Hire Dewakar S. - RAG Engineer

About dewakar

I'm a Backend Engineer specializing in building production-ready AI systems using Python, FastAPI, and LLM frameworks. My core focus is on Retrieval-Augmented Generation (RAG) — not just using it, but architecting it from scratch. At MindX, I independently designed and built a complete RAG system end-to-end — from document ingestion pipelines using Apache Tika, to Hybrid RAG retrieval combining vector search and keyword matching on MongoDB Atlas, to state-driven LLM workflows using LangGraph. I made the key technical decisions: choosing FastAPI over alternatives for its async performance, designing the chunking strategies, and migrating from local inference to Azure OpenAI for production scale.What I enjoy most is the intersection of solid backend engineering and applied AI — where clean API design meets intelligent systems that actually work in production. I'm currently open to Backend Engineer, AI/LLM Engineer, or GenAI Developer roles based in Tamil Nadu or Bengaluru, and open to remote opportunities across India. skills : Python · FastAPI · RAG · LangChain · LangGraph · Azure OpenAI · MongoDB Atlas · Vector Search · LLM Tool Calling · Microservices · REST APIs

Common Questions

Other RAG Engineers