4+ years designing and deploying production AI across public sector and enterprise — systems that handle real users, real data, and real failures.
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 at scale, now at Deloitte South Asia LLP as an Assistant Manager.
My core work sits at the intersection of multi-agent orchestration, RAG architecture, and LLMOps. I've built LangGraph multi-agent systems with intent-classification routing, constructed MCP servers for standardised tool integration, implemented hybrid RAG with cross-encoder re-ranking, and shipped embedding-based knowledge retrieval grounding LLM responses in verified documentation.
I take evaluation seriously. Anyone can wire together a RAG pipeline — not everyone can tell you whether it's working. I build RAGAS + DeepEval evaluation harnesses, custom LLM-as-Judge evaluators, and CI/CD gates that block deployments when faithfulness drops below threshold.
My production stack spans Azure, Databricks, Kubernetes, FastAPI, and Docker — systems load-tested at 100 concurrent users with real p99 latency numbers documented. Currently pursuing an MS in AI & Cybersecurity at IIT Patna alongside full-time work at Deloitte.
Production-verified across enterprise deployments and 6 portfolio projects — every skill has shipped code behind it.
Production systems across public sector and enterprise — not prototypes.
6 production systems and portfolio repos — backed by real code and real metrics.
Send a message directly — I read every one. Typical response within 24 hours.
Three mini-games built around the exact systems I build at work. See how well you know Agentic AI.