Ayush Rai

AI Engineer with 2+ years of experience building production LLM and GenAI systems. I work across backend, infrastructure, and product to ship practical AI solutions that run reliably at scale.

I’ve built RAG systems, AI agents, evaluation pipelines, and full-stack AI products end-to-end. My focus is on real-world constraints: latency, cost, reliability, and safety , not just demos.

Previously contributed to large-scale model improvement and evaluation projects with OpenAI, Scale AI, Snorkel AI, and Turing through partner programs.

Tech: Python, FastAPI, Node.js, React, PostgreSQL, Docker, LangChain, OpenAI API.

Currently building AI systems and consulting on production LLM workflows and evaluation.