Ten years of building production AI, mostly in the parts you don’t see — retrieval that doesn’t lie, evals that don’t lie either, and agents that politely admit when they’re wrong. Currently leading enterprise RAG delivery for a Tier-1 engagement; on weekends I run a 7,000-person practitioner community in Bangalore.
I think people hire engineers for results, not for buzzword bingo. So here’s the work, grouped by what it actually produces.
Compliance-grade retrieval pipelines that cite their sources and don’t make things up. Hybrid retrieval, reranking, chunking strategy that survives a 300-page PDF.
Eval harnesses that turn “vibes” into a number. RAGAS, TruLens, LLM-as-judge, regression suites that ship with every prompt change.
Multi-agent orchestration, tool calling, and MCP integrations — built so you can read the trace and understand exactly why it did what it did.
Taking AI pilots from prototype to production with governance, cost controls, and quality gates. The unglamorous middle of the lifecycle, owned end-to-end.
Pulled from the resume. Each one has a working artifact behind it — happy to walk through eval results, retrieval configs, or the bits that almost shipped sideways.
“Claude reads 300 pages of privacy law and cites its sources.”
End-to-end production RAG for a Tier-1 enterprise engagement: Claude Sonnet on Bedrock, Qdrant for hybrid retrieval, FastAPI orchestration, RAGAS gates. Running a formal head-to-head of PageIndex vs chunked-RAG with reranking, measuring faithfulness, context precision, latency, and per-query cost — the decision framework other compliance workflows now follow.
“222 asset classes, structured outputs, a multi-week process killed.”
LLM classifier on Claude/Bedrock for a regulated enterprise client: structured output validation, confidence scoring, rationale generation, and a human-in-the-loop review queue for audit defensibility. Replaced a multi-week manual categorization with near-real-time.
“A job-hunt copilot that actually reads the listings.”
Personal project, v0 global hackathon submission. Next.js + Neon Postgres + Apify scrapers on Vercel, with retrieval over my own work history and a small evaluator for fit. Currently being dogfooded on my own search.
“$10K and a year of validation.”
Winner of the AWS Global GenAI Hackathon. Claude on Bedrock with dynamic, context-aware question generation and RAG-grounded transcript evaluation against role competencies. Prompt orchestration, structured-output scoring, quality validation across both generated and evaluated content.
“A knowledge graph that explains itself to a pharmacist.”
Neo4j knowledge graph with LLM-based entity linking and a RAG retrieval interface for complex pharmacological queries, built for a large US healthcare deployment. Every response grounded to a source document with inline citation and auditor-visible provenance. Azure OpenAI + Azure AI Search.
“Multi-tenant B2B prospecting, wrapped in MCP.”
Multi-tenant B2B prospecting SaaS exposed as an MCP server. FastAPI + Anthropic MCP SDK. The clients pull leads through Claude — the agent does the boring part, the human does the call.
Started in analytics, ended up in production GenAI. The titles shifted; the work — turning messy real-world data into systems people can trust — didn’t.
Started in sports analytics and operational analytics; built predictive models, ETL pipelines, and early ML systems across sports, real estate, and infrastructure verticals.
Marketing Mix Modeling, real-time campaign optimization, user segmentation. First serious production ML work — the kind that has SLAs.
Transitioned into GenAI leadership. Built production RAG, knowledge graphs, and MLOps infrastructure. Won the AWS Global GenAI Hackathon during this period.
Leading enterprise RAG delivery, LLM evaluation frameworks, and AI governance for Tier-1 clients. Architecting parallel cloud-native reference implementations across AWS Bedrock and Azure OpenAI.
I lead the Bangalore chapter of The AI Collective — the largest practitioner community in India for production AI engineers. Since March 2025, we’ve shipped 40+ events, hosted speakers from across the ecosystem, and built the kind of room where people argue about eval harnesses and then go get dinner.
I publish small, sharp agent skills — opinionated prompts and tools designed to make Claude better at one specific thing. A few are below; the rest are in drafts.
I read everything. Best for: production RAG / eval consulting, DevRel conversations at AI-native companies, community collabs, or just a good thread about retrieval. Slow for: cold sales pitches.