Skip to content

Résumé

Divyansh Shukla

AI engineer · RAG & agentic systems

I architect production retrieval and agent systems on Azure, end to end. Ingestion pipelines, hybrid and agentic retrieval, LLM evaluation, and the network-isolated cloud infrastructure underneath, plus the full-stack apps people actually use. 5+ years shipping software.

Experience

  1. Agentic retrieval & evaluation-driven engineering

    2026 — now
    • Conversation-aware query planning over federated, purpose-built indexes
    • Structure-aware ingestion: layout parsing, table stitching, section-scoped chunking
    • Crash-safe Microsoft Graph delta sync into a compliance-grade search platform
    • LLM-as-judge evaluation of production traffic to drive retrieval redesigns
  2. Multi-agent systems

    2025
    • AutoGen AgentChat teams behind FastAPI with token streaming over WebSockets
    • Production switch-over of a public RAG assistant to an agentic architecture
    • Merged public and admin portals behind private networking and an application gateway
  3. RAG in production

    2024
    • Hybrid keyword + vector retrieval with semantic reranking and cited answers
    • Queue-driven serverless ingestion with OCR, layout analysis and token-aware batching
    • Multi-tenant document Q&A API with OCR ingestion and vector search
  4. Applied AI services

    2023
    • Early Azure OpenAI chat and document Q&A prototypes
    • Vision, speech, language and form-recognition services behind a Node API
  5. IoT platforms & digital twins

    2021 — 2022
    • React/TypeScript dashboards with Node/Express APIs over SQL Server and Cosmos DB
    • Device simulators streaming into IoT Hub, with serverless digital-twin graph sync

Selected projects

  1. Public-Records AI Assistant

    Production since 2024 · 2024–2026

    Lead engineer · retrieval, ingestion, evaluation & infra

    Architected and evolved a citation-grounded RAG assistant for a public-sector authority across four generations, from hybrid search with LLM query rewriting to Azure AI Search agentic retrieval over two federated indexes, driven by offline evaluation of production traffic.

  2. Lead engineer · ingestion, retrieval & infra

    Engineered an incremental SharePoint-to-Azure AI Search pipeline on Microsoft Graph delta, with resumable crawls, typed extraction from compliance PDFs and agentic hybrid retrieval behind a fail-closed audit trail.

  3. Aircraft Records Q&A and Validation

    Production · 2024–2025

    Engineer · ingestion, identifier search & LLM pipeline

    Engineered retrieval and extraction over scanned aircraft maintenance records: a queue-driven OCR and LLM ingestion pipeline, an identifier index with set-intersection queries, and JSON-mode spreadsheet validation returning cited dates, hours and cycles.

  4. Multi-Agent Advisory Workspace

    Proof of concept · 2025

    Lead backend engineer · agents, prompts & state

    Engineered a multi-agent AutoGen workspace serving five specialised agents behind one WebSocket chat, combining tool calling, hybrid-search grounding, deterministic code-side validation and per-user persisted team state for audit and deal-advisory work.

  5. Invoice and Expense Audit Assistant

    Proof of concept · 2025

    Lead backend engineer · validation pipeline & streaming

    Engineered a hybrid LLM and deterministic-rules audit pipeline that reconciles ERP records against OCR'd invoices and requisition forms, streaming field-level pass/fail verdicts to the browser over Server-Sent Events.

  6. Full-stack engineer · frontend, API & data

    Engineered a multi-site IoT monitoring platform: a config-driven React/TypeScript SPA and Express API over SQL Server that projects live sensor, occupancy and BLE asset telemetry onto annotated floor plans, shipped as customer-specific production builds.

12 more projects at divyanshshukla.dev/work.

Skills

AI & retrieval
Azure OpenAI (GPT-4o, 4.1, 5-series) · RAG architecture · Azure AI Search · hybrid + semantic · Agentic retrieval / knowledge bases · AutoGen multi-agent · Embeddings & vector indexes (HNSW) · Document Intelligence / OCR · LLM evaluation · LLM-as-judge · Prompt & tool design
Backend
Python · FastAPI · Quart · Node.js · Express · WebSockets & SSE streaming · REST API design · Microsoft Graph · Cosmos DB · SQL Server · Blob · Queue · Table storage · pytest · in-memory fakes
Frontend
TypeScript · React 19 · Vite · Angular (10 → 21) · Redux · MobX · Material UI · Fluent UI · Data viz · amCharts · Recharts · Azure Maps · MSAL / Entra ID sign-in
Cloud & infrastructure
Azure Functions · App Service · Container Apps · Private endpoints · VNet integration · Application Gateway · Managed identity · RBAC · Entra ID · Application Insights · IoT Hub · Event Grid · Digital Twins