Engineering Atlas

Reasoning becomes useful when context, tools and human decisions have explicit boundaries.

• Paired vector retrieval with graph traversal rather than shipping a plain RAG assistant.Research
  Engineering detail

  Vector search finds semantically similar things; graph traversal finds causally connected ones. Vector-only cannot answer what a change affects three hops away, and graph-only cannot read runbooks, tickets and email. Cross-domain operational reasoning needs both, so the hybrid is the technical core of the design.

  Discuss the designEnter this system
• Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
  Engineering detail

  Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

  Discuss the designEnter this system
• Fanned work out across asynchronous agents instead of one sequential pass.Production Pilot
  Engineering detail

  A linear pipeline times out on large monorepos. Parallel fan-out by module trades orchestration complexity for the ability to document a big codebase in a single run: the only way the tool stays usable at real repo sizes.

  Discuss the designEnter this system
• Extracted topology with deterministic parsers before the agent reasons over it.Enterprise Internal
  Engineering detail

  Structure is parsed by code and handed to the LLM as verified facts, so the agent reasons over real infrastructure instead of inventing components. Non-determinism is confined to synthesis, never to what exists.

  Discuss the designEnter this system

Contracts, tenant boundaries and data access shape the service, not just its endpoints.

• Enforced tenant isolation in PostgreSQL with Row-Level Security, not in the API layer.Enterprise Internal
  Engineering detail

  Database policies reduce reliance on every API remembering a tenant filter, at the cost of query and operational flexibility. Row-Level Security still needs correct role configuration, policy tests and controls for privileged access; it does not replace a full threat model or security testing.

  Discuss the designEnter this system
• Won latency back through indexing and query tuning before scaling hardware.Enterprise Production
  Engineering detail

  The 60% API improvement came from indexes, query optimisation and pagination across MongoDB and relational data: a cheaper, more durable fix than adding infrastructure to mask slow queries.

  Discuss the designEnter this system

Independent services trade coordination and operational cost for clearer boundaries and release freedom.

• Decomposed the platform into 12+ focused microservices over a shared monolith.Enterprise Production
  Engineering detail

  Independent services let 24+ features ship on their own cadence to 500+ orgs without one release train blocking everything. The operational cost of running many services was absorbed by CI/CD automation.

  Discuss the designEnter this system
• Distributed Software-Defined Network: overviewResearch
  Engineering detail

  A distributed SDN model with an accelerated Raft consensus algorithm that keeps multiple controllers consistent while scaling protocol handling. Top 8 of 200+ teams at the IEEE Kalpana 30Hr Hackathon.

  Discuss the design
• AI Software Development Engineer / Hewlett Packard Enterprise (HPE)Aug 2025 – Present
  Engineering detail

  Ship production AI systems and the Kubernetes-native platform services beneath them for HPE's Emerging Technologies team. Architected HPE OpsNexus, an enterprise operations intelligence mesh that unifies siloed operational systems into a knowledge graph and reasons across domains to predict downstream business impact. It ranked #1 in HPE's FOCUS AI Ideathon 2026 and was taken to final review before the FOCUS Group leadership panel. Engineered 7 production-grade AI systems and the distributed backend services beneath them within HPE's Emerging Technologies Team, automating complex enterprise engineering workflows and giving engineers their time back. Architected 8 Kubernetes-native microservices and 16 modular AI orchestration services for scalable AI platforms, powering intelligent incident classification, retrieval-augmented generation, and the generation of 450+ standardized documents. Developed AI-powered workflow automation with human-in-the-loop (HITL) decision support wired into enterprise systems, reducing manual operational effort by 42%. Designed MLOps pipelines for multiple models across hybrid-cloud environments, alongside sustainable automation that improved infrastructure visibility and eliminated 14 engineering hours of manual analysis every week. Modernized legacy enterprise applications by migrating 16 backend services and their databases to containerized, cloud-native architectures, standardizing deployment, observability and rollback across the platform estate. Partnered with software, cloud and platform engineering teams across 4+ business units to deliver HPE OneAI, applying modern software engineering, DevOps and cloud-native practices. Contributing to Agentic & Augmented AI orchestration that integrates adaptive learning and real-time feedback (RLHF) for self-optimizing systems. Ramped rapidly on Red Hat OpenShift, OpenStack and HPE Ezmeral to support key enterprise accounts, sustaining platform stability through routine health checks, fast issue resolution, and clear operational SOPs (recognized in HPE's Points Recognition program). Endorsed by the Director of HPE Managed Services, with the recommendation published in HPE's magazine.

  Discuss the design

The runtime, deployment process and operational handover are part of the software.

• Cloud Engineering Intern / Hewlett Packard Enterprise (HPE)Feb 2025 – Jul 2025
  Engineering detail

  Automate secure, scalable infrastructure across AWS, Azure and HPE GreenLake. Engineered automation scripts and Ansible playbooks to streamline deployment pipelines and enhance infrastructure reliability across multi-cloud environments. Designed and tested cloud-native architectures with AWS, Azure, and HPE GreenLake, optimizing resource allocation and supporting scalable, elastic applications. Developed microservice packaging strategies with Docker and explored container orchestration using Kubernetes for modular application lifecycles. Configured secure Linux environments with RHEL system management, including ACL-based permissions, SELinux tuning, and network segmentation.

  Discuss the design
• AWS / GTMScaleEnterprise Production
  Engineering detail

  AWS is part of GTMScale's technology stack.

  Discuss the designEnter this system
• Derived design from live IaC and Kubernetes state, not the CMDB.Enterprise Internal
  Engineering detail

  ITSM approvals were being rejected for inaccurate topology. Reading the actual Terraform and Kubernetes manifests, the real source of truth, removed the drift that documentation-based mapping always accumulates.

  Discuss the designEnter this system

Container orchestration and infrastructure topology connect application intent to running services.

• Kubernetes / Hexus – Smart Log ManagerEnterprise Internal
  Engineering detail

  Kubernetes is part of Hexus – Smart Log Manager's technology stack.

  Discuss the designEnter this system
• Agentic AIOps Blueprint: IaC / K8sEnterprise Internal
  Engineering detail

  Terraform and Kubernetes manifests supply resource definitions instead of manually maintained topology descriptions.

  Discuss the designEnter this system
• Cloud Engineering Intern / Hewlett Packard Enterprise (HPE)Feb 2025 – Jul 2025
  Engineering detail

  Automate secure, scalable infrastructure across AWS, Azure and HPE GreenLake. Engineered automation scripts and Ansible playbooks to streamline deployment pipelines and enhance infrastructure reliability across multi-cloud environments. Designed and tested cloud-native architectures with AWS, Azure, and HPE GreenLake, optimizing resource allocation and supporting scalable, elastic applications. Developed microservice packaging strategies with Docker and explored container orchestration using Kubernetes for modular application lifecycles. Configured secure Linux environments with RHEL system management, including ACL-based permissions, SELinux tuning, and network segmentation.

  Discuss the design

An interface, API and data model should explain the same product.

• GTMScale: overviewEnterprise Production
  Engineering detail

  A microservice-based B2B SaaS ERP (MERN + AWS) powering 500+ healthcare organizations, with 24+ features, real-time dashboards and sales trackers, hardened by JWT auth and automated testing across 750+ CI/CD deployments.

  Discuss the designEnter this system
• Hexus – Smart Log Manager: Micro-FrontendEnterprise Internal
  Engineering detail

  The federated React frontend exposes model management and training observability.

  Discuss the designEnter this system
• NetworkNex: overviewLive Deployment
  Engineering detail

  A LinkedIn-style app with API integration, a dynamic feed, dark mode and secure Google-based session management, built on Next.js, the MERN stack and Prisma.

  Discuss the design
• Ticket Snatcher: overviewLive Deployment
  Engineering detail

  A MERN movie-booking app. Theatre and showtime filters narrow the catalogue to a single screening, an interactive seat map carries reservation state per seat, and an Express API over MongoDB persists the booking. Deployed on Vercel.

  Discuss the design
• My Keeper: overviewLive Deployment
  Engineering detail

  A React note manager with full create, read, update and delete over component state, an expanding composer that stays collapsed until focused, and a responsive card board. Deployed on Vercel.

  Discuss the design

Training, activation, evaluation and operating a model belong to one lifecycle.

• AI Software Development Engineer / Hewlett Packard Enterprise (HPE)Aug 2025 – Present
  Engineering detail

  Ship production AI systems and the Kubernetes-native platform services beneath them for HPE's Emerging Technologies team. Architected HPE OpsNexus, an enterprise operations intelligence mesh that unifies siloed operational systems into a knowledge graph and reasons across domains to predict downstream business impact. It ranked #1 in HPE's FOCUS AI Ideathon 2026 and was taken to final review before the FOCUS Group leadership panel. Engineered 7 production-grade AI systems and the distributed backend services beneath them within HPE's Emerging Technologies Team, automating complex enterprise engineering workflows and giving engineers their time back. Architected 8 Kubernetes-native microservices and 16 modular AI orchestration services for scalable AI platforms, powering intelligent incident classification, retrieval-augmented generation, and the generation of 450+ standardized documents. Developed AI-powered workflow automation with human-in-the-loop (HITL) decision support wired into enterprise systems, reducing manual operational effort by 42%. Designed MLOps pipelines for multiple models across hybrid-cloud environments, alongside sustainable automation that improved infrastructure visibility and eliminated 14 engineering hours of manual analysis every week. Modernized legacy enterprise applications by migrating 16 backend services and their databases to containerized, cloud-native architectures, standardizing deployment, observability and rollback across the platform estate. Partnered with software, cloud and platform engineering teams across 4+ business units to deliver HPE OneAI, applying modern software engineering, DevOps and cloud-native practices. Contributing to Agentic & Augmented AI orchestration that integrates adaptive learning and real-time feedback (RLHF) for self-optimizing systems. Ramped rapidly on Red Hat OpenShift, OpenStack and HPE Ezmeral to support key enterprise accounts, sustaining platform stability through routine health checks, fast issue resolution, and clear operational SOPs (recognized in HPE's Points Recognition program). Endorsed by the Director of HPE Managed Services, with the recommendation published in HPE's magazine.

  Discuss the design
• Hexus – Smart Log Manager: Anomaly MLEnterprise Internal
  Engineering detail

  Use Isolation Forest and LOF for unsupervised anomaly detection, with supervised scoring as labels accumulate.

  Discuss the designEnter this system
• Multi-Modal AI Speech Coach: overviewLive Deployment
  Engineering detail

  An AI-driven app that personalises interactive coaching prompts with real-time LLM workflows, pairing TensorFlow speech analysis with a dynamic ReactJS UI. Top 6 at the Nex-Gen AI 24Hr Hackathon.

  Discuss the design
• HRBIRS: overviewResearch
  Engineering detail

  Principal-Author research on a blockchain-based recruitment system using Ethereum + Solidity (PoS) for secure, immutable data, paired with a hybrid TF-IDF recommendation engine achieving 85% precision. Published at ICT4SD 2025.

  Discuss the design

Identity, secrets, tenant isolation and redaction must protect the data before reasoning begins.

• Anonymised PII at ingestion with Presidio + spaCy, not on read.Enterprise Internal
  Engineering detail

  Stripping sensitive data before it lands in storage or reaches the LLM is a stricter boundary than redacting at query time. The reprocessing overhead is far cheaper than the blast radius of a leak.

  Discuss the designEnter this system
• Enforced tenant isolation in PostgreSQL with Row-Level Security, not in the API layer.Enterprise Internal
  Engineering detail

  Database policies reduce reliance on every API remembering a tenant filter, at the cost of query and operational flexibility. Row-Level Security still needs correct role configuration, policy tests and controls for privileged access; it does not replace a full threat model or security testing.

  Discuss the designEnter this system
• Captured entitlement metadata at ingestion instead of filtering only at query time.Research
  Engineering detail

  If access control is applied late, retrieval can assemble an answer from records the requester is not entitled to see. Binding entitlement metadata at ingestion supports permission-aware retrieval, but enforcement still depends on correct query-time checks, current permissions and tested policies.

  Discuss the designEnter this system
• GTMScale: API GatewayEnterprise Production
  Engineering detail

  Authenticate API access with JWT and route requests into the ERP services.

  Discuss the designEnter this system

Make repeated engineering work reproducible, reviewable and connected to its source.

• Wired generation into CI/CD rather than a manual 'generate docs' step.Production Pilot
  Engineering detail

  CI/CD makes regeneration part of a code change rather than a separate manual task. Failed jobs, uncovered modules and semantic inaccuracies can still leave gaps, so freshness checks and human review remain necessary.

  Discuss the designEnter this system
• Emitted native, compliant Word / SOP artifacts in the exact format ITSM already requires.Enterprise Internal
  Engineering detail

  Compliance reviewers live in fixed Word templates. Generating those deliverables directly eliminated manual reformatting entirely, a larger operational win than asking an org to adopt a new tool.

  Discuss the designEnter this system
• Cloud Engineering Intern / Hewlett Packard Enterprise (HPE)Feb 2025 – Jul 2025
  Engineering detail

  Automate secure, scalable infrastructure across AWS, Azure and HPE GreenLake. Engineered automation scripts and Ansible playbooks to streamline deployment pipelines and enhance infrastructure reliability across multi-cloud environments. Designed and tested cloud-native architectures with AWS, Azure, and HPE GreenLake, optimizing resource allocation and supporting scalable, elastic applications. Developed microservice packaging strategies with Docker and explored container orchestration using Kubernetes for modular application lifecycles. Configured secure Linux environments with RHEL system management, including ACL-based permissions, SELinux tuning, and network segmentation.

  Discuss the design

Make architecture inspectable while keeping the text, keyboard and mobile experience complete.

• This portfolioInteractive implementation
  Engineering detail

  This portfolio combines server-rendered Next.js and React content with Three.js spatial architecture, instanced geometry, demand rendering, keyboard inspection and a contextual AI Twin.

  Discuss the design

1. User

   A bounded request enters the system. Intent is captured before any tool or model can act.

   • Hexus – Smart Log Manager: OperatorsEnterprise Internal
     Engineering detail

     ITOps and SRE users investigate incidents through the application interface.

     Discuss the designEnter this system

2. Frontend

   Expose the request and its state. People need to see what the system accepted and what is still pending.

   • Hexus – Smart Log Manager: Micro-FrontendEnterprise Internal
     Engineering detail

     The federated React frontend exposes model management and training observability.

     Discuss the designEnter this system

3. API

   Check the contract and identity. Authentication and tenant policy are boundaries, not a prompt instruction.

   • Hexus – Smart Log Manager: FastAPI APIEnterprise Internal
     Engineering detail

     Coordinate ingestion, anomaly detection, semantic retrieval, training and activation through tenant-aware APIs.

     Discuss the designEnter this system
   • Enforced tenant isolation in PostgreSQL with Row-Level Security, not in the API layer.Enterprise Internal
     Engineering detail

     Database policies reduce reliance on every API remembering a tenant filter, at the cost of query and operational flexibility. Row-Level Security still needs correct role configuration, policy tests and controls for privileged access; it does not replace a full threat model or security testing.

     Discuss the designEnter this system

4. Intent

   Choose a supported workflow. A constrained plan prevents an open-ended request from becoming an unrestricted action.

   • HPE OpsNexus: Agent OrchestrationResearch
     Engineering detail

     Coordinate the planner, registered MCP tools and durable reasoning steps, with human approval as an explicit gate.

     Discuss the designEnter this system

5. Orchestrator

   Coordinate reasoning and tool steps. State, typed tools and timeouts keep a failed step local.

   • Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
     Engineering detail

     Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

     Discuss the designEnter this system

6. Retrieval

   Select relevant, permitted context. The proposed graph and retrieval path keeps relationships alongside documents.

   • Paired vector retrieval with graph traversal rather than shipping a plain RAG assistant.Research
     Engineering detail

     Vector search finds semantically similar things; graph traversal finds causally connected ones. Vector-only cannot answer what a change affects three hops away, and graph-only cannot read runbooks, tickets and email. Cross-domain operational reasoning needs both, so the hybrid is the technical core of the design.

     Discuss the designEnter this system
   • Captured entitlement metadata at ingestion instead of filtering only at query time.Research
     Engineering detail

     If access control is applied late, retrieval can assemble an answer from records the requester is not entitled to see. Binding entitlement metadata at ingestion supports permission-aware retrieval, but enforcement still depends on correct query-time checks, current permissions and tested policies.

     Discuss the designEnter this system

7. Model

   Synthesize over supplied context. Generated prose is separate from the facts and contracts that constrain it.

   • RapidDoc AI: Azure OpenAIProduction Pilot
     Engineering detail

     Generate prose from extracted code structure for engineering review.

     Discuss the designEnter this system

8. Tool

   Execute a registered operation. A typed interface bounds what orchestration can request.

   • HPE OpsNexus: Agent OrchestrationResearch
     Engineering detail

     Coordinate the planner, registered MCP tools and durable reasoning steps, with human approval as an explicit gate.

     Discuss the designEnter this system

9. Infrastructure

   Host the service and its dependencies. Application behavior also depends on the container and cloud runtime.

   • Cloud Engineering Intern / Hewlett Packard Enterprise (HPE)Feb 2025 – Jul 2025
     Engineering detail

     Automate secure, scalable infrastructure across AWS, Azure and HPE GreenLake. Engineered automation scripts and Ansible playbooks to streamline deployment pipelines and enhance infrastructure reliability across multi-cloud environments. Designed and tested cloud-native architectures with AWS, Azure, and HPE GreenLake, optimizing resource allocation and supporting scalable, elastic applications. Developed microservice packaging strategies with Docker and explored container orchestration using Kubernetes for modular application lifecycles. Configured secure Linux environments with RHEL system management, including ACL-based permissions, SELinux tuning, and network segmentation.

     Discuss the design
   • Docker / Hexus – Smart Log ManagerEnterprise Internal
     Engineering detail

     Docker is part of Hexus – Smart Log Manager's technology stack.

     Discuss the designEnter this system

10. Validation

    Check the output against explicit criteria. A plausible response must still satisfy a schema and its evidence boundary.

    • Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
      Engineering detail

      Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

      Discuss the designEnter this system

11. Human approval

    Pause at the decision boundary. The OpsNexus research design makes human approval an architectural gate.

    • HPE OpsNexus: Agent OrchestrationResearch
      Engineering detail

      Coordinate the planner, registered MCP tools and durable reasoning steps, with human approval as an explicit gate.

      Discuss the designEnter this system

12. Action

    Apply only the approved operation. Approval and execution are separate states in this local synthesis.

    • AI Software Development Engineer / Hewlett Packard Enterprise (HPE)Aug 2025 – Present
      Engineering detail

      Ship production AI systems and the Kubernetes-native platform services beneath them for HPE's Emerging Technologies team. Architected HPE OpsNexus, an enterprise operations intelligence mesh that unifies siloed operational systems into a knowledge graph and reasons across domains to predict downstream business impact. It ranked #1 in HPE's FOCUS AI Ideathon 2026 and was taken to final review before the FOCUS Group leadership panel. Engineered 7 production-grade AI systems and the distributed backend services beneath them within HPE's Emerging Technologies Team, automating complex enterprise engineering workflows and giving engineers their time back. Architected 8 Kubernetes-native microservices and 16 modular AI orchestration services for scalable AI platforms, powering intelligent incident classification, retrieval-augmented generation, and the generation of 450+ standardized documents. Developed AI-powered workflow automation with human-in-the-loop (HITL) decision support wired into enterprise systems, reducing manual operational effort by 42%. Designed MLOps pipelines for multiple models across hybrid-cloud environments, alongside sustainable automation that improved infrastructure visibility and eliminated 14 engineering hours of manual analysis every week. Modernized legacy enterprise applications by migrating 16 backend services and their databases to containerized, cloud-native architectures, standardizing deployment, observability and rollback across the platform estate. Partnered with software, cloud and platform engineering teams across 4+ business units to deliver HPE OneAI, applying modern software engineering, DevOps and cloud-native practices. Contributing to Agentic & Augmented AI orchestration that integrates adaptive learning and real-time feedback (RLHF) for self-optimizing systems. Ramped rapidly on Red Hat OpenShift, OpenStack and HPE Ezmeral to support key enterprise accounts, sustaining platform stability through routine health checks, fast issue resolution, and clear operational SOPs (recognized in HPE's Points Recognition program). Endorsed by the Director of HPE Managed Services, with the recommendation published in HPE's magazine.

      Discuss the design

13. Outcome

    Return an inspectable result. Outcome and overrides close the proposed operational-memory loop.

    • HPE OpsNexus: Learning LoopResearch
      Engineering detail

      Feed outcomes and overrides back into operational memory. This is a design loop, not live telemetry from HPE.

      Discuss the designEnter this system

1. Gateway

   Authenticate and route incoming traffic. A clear API boundary connects clients to independent services.

   • GTMScale: API GatewayEnterprise Production
     Engineering detail

     Authenticate API access with JWT and route requests into the ERP services.

     Discuss the designEnter this system

2. Services

   Own independent product responsibilities. GTMScale's service boundaries support separate release cadences.

   • Decomposed the platform into 12+ focused microservices over a shared monolith.Enterprise Production
     Engineering detail

     Independent services let 24+ features ship on their own cadence to 500+ orgs without one release train blocking everything. The operational cost of running many services was absorbed by CI/CD automation.

     Discuss the designEnter this system

3. Cache

   An illustrative fast-read branch. This fixture can miss without stopping the primary data path. It is not a GTMScale architecture claim.

4. Database

   Persist operational and relational records. Query tuning, indexes and pagination control work before additional infrastructure.

   • Won latency back through indexing and query tuning before scaling hardware.Enterprise Production
     Engineering detail

     The 60% API improvement came from indexes, query optimisation and pagination across MongoDB and relational data: a cheaper, more durable fix than adding infrastructure to mask slow queries.

     Discuss the designEnter this system

5. Queue

   An illustrative asynchronous boundary. Pending work can wait while a worker recovers; this queue is a local simulation component.

6. Worker

   Consume one captured unit of work. The fixture retries a failed worker without replaying completed request stages.

7. External service

   A separately owned dependency. The OpsNexus design consumes published APIs rather than replacing systems of record.

   • Consumed the existing systems of record instead of building a new data platform.Research
     Engineering detail

     Reading GreenLake, OpsRamp, ServiceNow and SAP through their published APIs avoids replacing the systems of record. Connector development, entitlement mapping and operational support still require engineering work; the design reuses existing platforms rather than introducing a competing data platform.

     Discuss the designEnter this system

8. Retry boundary

   Bound the recovery attempt. The representative worker branch stops after its configured retry budget.

   • Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
     Engineering detail

     Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

     Discuss the designEnter this system

9. Observability

   Expose service state and signals. The operator needs to distinguish an affected dependency from a healthy branch.

   • Hexus – Smart Log Manager: ObservabilityEnterprise Internal
     Engineering detail

     Expose operational metrics and logs for the platform and its training workflows.

     Discuss the designEnter this system

10. Delivery

    Test and release services. Release automation absorbs some of the operational cost of independent services.

    • Gated every one of 750+ deploys behind automated tests.Enterprise Production
      Engineering detail

      Continuous deployment to production healthcare tenants only works if releases are safe by default. Test gates cut bug reports 50% and let a small team ship continuously without breaking production.

      Discuss the designEnter this system

1. Planner

   Decompose a supported task. OpsNexus proposes durable reasoning steps, rather than one unbounded prompt.

   • HPE OpsNexus: Agent OrchestrationResearch
     Engineering detail

     Coordinate the planner, registered MCP tools and durable reasoning steps, with human approval as an explicit gate.

     Discuss the designEnter this system

2. Context

   Carry extracted facts into reasoning. RapidDoc extracts source structure before language-model authoring.

   • Grounded generation in deterministic static analysis, not the model alone.Production Pilot
     Engineering detail

     Imports, ASTs, dependency graphs and call relations are extracted by code and diagrams synthesised programmatically. The LLM writes prose over verified structure, so docs describe the real system rather than a plausible-sounding one.

     Discuss the designEnter this system

3. Retrieval

   Find supporting context. Graph traversal and document retrieval answer different parts of an operational question.

   • Paired vector retrieval with graph traversal rather than shipping a plain RAG assistant.Research
     Engineering detail

     Vector search finds semantically similar things; graph traversal finds causally connected ones. Vector-only cannot answer what a change affects three hops away, and graph-only cannot read runbooks, tickets and email. Cross-domain operational reasoning needs both, so the hybrid is the technical core of the design.

     Discuss the designEnter this system

4. Parallel agents

   Fan work out by responsibility. RapidDoc trades coordination complexity for parallel documentation work.

   • Fanned work out across asynchronous agents instead of one sequential pass.Production Pilot
     Engineering detail

     A linear pipeline times out on large monorepos. Parallel fan-out by module trades orchestration complexity for the ability to document a big codebase in a single run: the only way the tool stays usable at real repo sizes.

     Discuss the designEnter this system

5. Tools

   Constrain executable operations. Typed tools and timeouts place boundaries around the Hexus RCA workflow.

   • Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
     Engineering detail

     Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

     Discuss the designEnter this system

6. Memory

   Connect prior decisions and outcomes. The proposed OpsNexus memory graph distinguishes operational history from transient context.

   • HPE OpsNexus: Knowledge + MemoryResearch
     Engineering detail

     Connect assets, services and dependencies with a memory of prior decisions, fixes and outcomes.

     Discuss the designEnter this system

7. Evaluation

   Inspect a result before it advances. Schema checks are a guard; they are not evidence that every generated statement is true.

   • Ran RCA as a guarded LangGraph state machine rather than a free-form prompt chain.Enterprise Internal
     Engineering detail

     Typed tools, timeouts and schema validation around every model call keep reasoning auditable and isolate failures to a single node. That is what minimises hallucinated incident statements: the difference between a demo and something an SRE trusts at 3am.

     Discuss the designEnter this system

8. Human gate

   Approve or reject the proposed action. The OpsNexus design includes human approval as an explicit architectural component.

   • HPE OpsNexus: Agent OrchestrationResearch
     Engineering detail

     Coordinate the planner, registered MCP tools and durable reasoning steps, with human approval as an explicit gate.

     Discuss the designEnter this system

9. Feedback

   Record the outcome and override. A feedback path should retain the context of the decision it follows.

   • HPE OpsNexus: Learning LoopResearch
     Engineering detail

     Feed outcomes and overrides back into operational memory. This is a design loop, not live telemetry from HPE.

     Discuss the designEnter this system

1. Idea

   Name the problem and the intended outcome. The project problem statements establish what each system was built to change.

   • GTMScale: problemEnterprise Production
     Engineering detail

     Healthcare organizations needed a reliable, fast, multi-tenant ERP for day-to-day operations and analytics, shipped continuously without breaking production.

     Discuss the designEnter this system

2. Design

   Choose boundaries and trade-offs. Architecture decisions determine what can evolve independently.

   • Decomposed the platform into 12+ focused microservices over a shared monolith.Enterprise Production
     Engineering detail

     Independent services let 24+ features ship on their own cadence to 500+ orgs without one release train blocking everything. The operational cost of running many services was absorbed by CI/CD automation.

     Discuss the designEnter this system

3. Code

   Implement behavior and extract structure. RapidDoc uses code-derived relationships as the input to documentation.

   • RapidDoc AI: Static AnalysisProduction Pilot
     Engineering detail

     Extract ASTs, imports, dependencies and call relations deterministically before language-model synthesis.

     Discuss the designEnter this system

4. Test

   Stop a broken change before release. GTMScale's automated test gates support continuous service delivery.

   • Gated every one of 750+ deploys behind automated tests.Enterprise Production
     Engineering detail

     Continuous deployment to production healthcare tenants only works if releases are safe by default. Test gates cut bug reports 50% and let a small team ship continuously without breaking production.

     Discuss the designEnter this system

5. Container

   Package the service with a runtime boundary. HPE cloud work includes Docker packaging and Kubernetes orchestration.

   • Cloud Engineering Intern / Hewlett Packard Enterprise (HPE)Feb 2025 – Jul 2025
     Engineering detail

     Automate secure, scalable infrastructure across AWS, Azure and HPE GreenLake. Engineered automation scripts and Ansible playbooks to streamline deployment pipelines and enhance infrastructure reliability across multi-cloud environments. Designed and tested cloud-native architectures with AWS, Azure, and HPE GreenLake, optimizing resource allocation and supporting scalable, elastic applications. Developed microservice packaging strategies with Docker and explored container orchestration using Kubernetes for modular application lifecycles. Configured secure Linux environments with RHEL system management, including ACL-based permissions, SELinux tuning, and network segmentation.

     Discuss the design

6. Deploy

   Release the artifact and its handover material. AIOps connects infrastructure changes to operational design documents; GTMScale releases services.

   • GTMScale: CI/CDEnterprise Production
     Engineering detail

     Automate testing and service releases across the ERP's independently deployed services.

     Discuss the designEnter this system
   • Agentic AIOps Blueprint: CI/CD PipelinesEnterprise Internal
     Engineering detail

     Infrastructure changes trigger regeneration of operational handover artifacts.

     Discuss the designEnter this system

7. Observe

   Inspect behavior in its operating context. HPE platform work brings deployment, observability and rollback into the application lifecycle.

   • AI Software Development Engineer / Hewlett Packard Enterprise (HPE)Aug 2025 – Present
     Engineering detail

     Ship production AI systems and the Kubernetes-native platform services beneath them for HPE's Emerging Technologies team. Architected HPE OpsNexus, an enterprise operations intelligence mesh that unifies siloed operational systems into a knowledge graph and reasons across domains to predict downstream business impact. It ranked #1 in HPE's FOCUS AI Ideathon 2026 and was taken to final review before the FOCUS Group leadership panel. Engineered 7 production-grade AI systems and the distributed backend services beneath them within HPE's Emerging Technologies Team, automating complex enterprise engineering workflows and giving engineers their time back. Architected 8 Kubernetes-native microservices and 16 modular AI orchestration services for scalable AI platforms, powering intelligent incident classification, retrieval-augmented generation, and the generation of 450+ standardized documents. Developed AI-powered workflow automation with human-in-the-loop (HITL) decision support wired into enterprise systems, reducing manual operational effort by 42%. Designed MLOps pipelines for multiple models across hybrid-cloud environments, alongside sustainable automation that improved infrastructure visibility and eliminated 14 engineering hours of manual analysis every week. Modernized legacy enterprise applications by migrating 16 backend services and their databases to containerized, cloud-native architectures, standardizing deployment, observability and rollback across the platform estate. Partnered with software, cloud and platform engineering teams across 4+ business units to deliver HPE OneAI, applying modern software engineering, DevOps and cloud-native practices. Contributing to Agentic & Augmented AI orchestration that integrates adaptive learning and real-time feedback (RLHF) for self-optimizing systems. Ramped rapidly on Red Hat OpenShift, OpenStack and HPE Ezmeral to support key enterprise accounts, sustaining platform stability through routine health checks, fast issue resolution, and clear operational SOPs (recognized in HPE's Points Recognition program). Endorsed by the Director of HPE Managed Services, with the recommendation published in HPE's magazine.

     Discuss the design

8. Improve

   Feed evidence into the next change. Query optimization and CI regeneration are concrete examples of iterative engineering.

   • Won latency back through indexing and query tuning before scaling hardware.Enterprise Production
     Engineering detail

     The 60% API improvement came from indexes, query optimisation and pagination across MongoDB and relational data: a cheaper, more durable fix than adding infrastructure to mask slow queries.

     Discuss the designEnter this system
   • Wired generation into CI/CD rather than a manual 'generate docs' step.Production Pilot
     Engineering detail

     CI/CD makes regeneration part of a code change rather than a separate manual task. Failed jobs, uncovered modules and semantic inaccuracies can still leave gaps, so freshness checks and human review remain necessary.

     Discuss the designEnter this system