Software Engineer · GenAI Engineer — Tech Lead at Tricon Infotech, Bengaluru.
~5 years building production backend systems, the last ~2 focused on Generative AI: LLM applications, RAG pipelines, and multi-agent systems. I own systems end-to-end — architecture → backend services → cloud infrastructure → production launch — including a multi-tenant healthcare RAG platform load-tested at 2,000+ concurrent sessions with sub-second latency.
🌐 Portfolio · 💼 LinkedIn · ✉️ rai.manas12@gmail.com
| Project | What it does |
|---|---|
| DevFlow Kit (site) | Multi-agent SDLC automation — turns Jira tickets into production PRs with zero added infrastructure; cuts the ticket-to-PR cycle from days to hours |
| RegLens (site) | Multi-agent regulatory compliance automation — extracts obligations, gap-checks them against your policies via RAG, and produces risk-scored audit reports with human-in-the-loop review |
| CostTracker | Open-source, self-hosted LLM cost tracking — drop-in SDK for OpenAI/Anthropic/Groq/Bedrock with real-time token metering and per-request cost attribution |
| Cloud Waste Hunter | ML-powered cloud waste detection — flags idle resources and eliminates them safely with dry-run previews, approvals, and rollback |
Backend — Python · Go · FastAPI · async microservices · WebSockets · SQLAlchemy GenAI — LangGraph · LangChain · Claude API · OpenAI API · MCP · Google ADK · RAG · RAGAS · vector databases (pgvector, Pinecone, FAISS, Neo4j) Cloud — AWS (ECS, Lambda, Bedrock, Cognito) · Azure OpenAI · Docker · Kubernetes · CI/CD
- Building with the Claude API — Anthropic Academy
- Introduction to Model Context Protocol (MCP) — Anthropic Academy
- Claude Code in Action — Anthropic Academy