Engineer who builds and ships AI systems end-to-end — from multi-agent LLM orchestration and RAG pipelines to event-driven backends and production deployments. Response latency <2s. Query accuracy 92%.
Engineer who builds and ships AI systems — from multi-agent LLM orchestration to production backends. Track record of cutting response latency to <2s and hitting 92% accuracy on unstructured data.
Core expertise: LangChain/LangGraph multi-agent systems, FastAPI backends with JWT/OAuth2, Redis event queues, RAG pipelines with FAISS, and full-stack deployment (Docker, CI/CD, Vercel/Render).
Comfortable owning architecture decisions, moving fast, and delivering working software that people actually use.
A platform that leverages LLMs and RAG pipelines to generate, summarize, and moderate content at scale. Integrates LangChain, FastAPI, and full-stack deployment.
Conversational AI for career guidance, resume review, and job matching. Built with LLMs, semantic search, and deployed with CI/CD pipelines.
I'm always open to collaborating on AI, Machine Learning, or NLP-driven projects. Whether you're building something innovative or exploring research ideas — let's connect and make it happen!