I build production-grade AI systems . Over the last 6+ years, I’ve worked in fast-paced startups designing and shipping systems that handle real users, real scale, and real constraints. My focus is on turning LLMs and ML models into reliable, low-latency, and cost-efficient products. I’ve worked across the stack—from model integration and retrieval systems to orchestration, infrastructure, and deployment—with a strong emphasis on making systems actually work in production. What I work on: LLM systems (Agents, RAG, Copilots) Retrieval & search (semantic + hybrid) Low-latency, scalable ML systems MLOps & production infrastructure