Sanju Preetham Simhachalam

I am an AI Engineer specializing in Generative AI, Retrieval-Augmented Generation (RAG), and LLM-powered systems. I build and deploy scalable AI applications using LangChain, LangGraph, and cloud platforms like AWS and GCP. I am an IEEE-published researcher with a track record of productionizing AI systems.

My work focuses on designing and deploying end-to-end AI solutions, including multi-step agents, embedding pipelines, and semantic search. I ship production-ready applications (FastAPI + React) and manage containerized deployments on AWS and GCP with Terraform, turning research ideas into robust, scalable systems and collaborating across teams to deliver impact.