AI/Full-stack Engineer

Divyanshu Sharma is an AI/Full-stack Engineer with 3 years of experience across Amazon, NYU research, and high-growth startups. They are currently building Elliot AI, a production AI companion with hybrid RAG memory (pgvector + SQL scoring, <300ms retrieval across 6+ months of history), intent-based tool routing that cut LLM costs 68%, and voice I/O - serving 50+ daily active sessions. Previously at Amazon, they drove $2.1M+ in annualized revenue impact through A/B experimentation across microservices. Before that, they scaled a startup's email platform from 400K to 1.5M+ daily sends. Divyanshu has also published in IEEE ICIP 2021 on zero-shot action recognition. They are looking for AI engineer / applied AI / full-stack roles at startups building LLM-powered products, having shipped RAG pipelines, inference optimization, and LLM-powered OCR in production. They require STEM-OPT (no sponsorship cost to employer).