Akash Chaudhari

I build AI systems that actually ship.
Over the past 4 years I've designed and deployed production-grade Generative AI and Agentic AI systems - first for the Government of Maharashtra, now at Deloitte. Not prototypes. Not demos. Systems that handle real users, real data, and real failure modes. My core work sits at the intersection of multi-agent orchestration, RAG architecture, and LLMOps. I've built LangGraph multi-agent systems routing natural-language queries to specialist agents, embedding-based knowledge retrieval pipelines grounding LLM responses in verified documentation, and LLM backend services with Pydantic validation, structured outputs, and circuit-breaker error handling - deployed on Azure with CI/CD and load-tested under production traffic.

What I care most about evaluation?
Anyone can wire together a RAG pipeline. Not everyone can tell you whether it's working - measuring faithfulness, context precision, and groundedness with RAGAS and DeepEval, tracing agent decisions with LangSmith, and building the automated test infrastructure that catches regressions before they reach users. Currently pursuing an MS in AI & Cybersecurity at IIT Patna alongside full-time work at Deloitte. Open to Agentic AI / LLM Engineer roles - remote-first, with EU and UK timezone overlap preferred.

📩 ag.chaudhari.1512@gmail.com