Senior AI Engineer with 6+ years building production-grade backend systems and intelligent LLM applications. Specialising in agentic AI, RAG pipelines, and multi-provider LLM orchestration.
Building LLM-powered agents with dynamic tool routing and orchestration using MCP protocol.
End-to-end retrieval-augmented generation — chunking, embedding, retrieval tuning, and evaluation.
Production-grade REST APIs, data pipelines, and scalable backend systems built with Python.
Multi-provider LLM orchestration with failover logic, rate limiting, and environment-based routing.
Measuring and improving AI output quality using RAGAS metrics, faithfulness scoring, and relevancy evaluation.
AWS-based deployments with serverless vector stores, caching layers, and observability pipelines.