New York, New York, United States
Tech Lead with 8+ years of experience in ML and AI Infra. * Built the first GPU retrieval inference and serving systems for FB Marketplace and Dating. * Distributed inference and training in extra-large Foundation Models.
Inference Efficiency for Foundation models. Over $6M+ saved in Q1 2026.
Led a workstream of 10+ eng to build the first GPU-based retrieval system for FB Marketplace and Dating, increasing product DAU by 0.2%+.
Co-founded an healthcare AI startup and grew it to 300k+ ARR. Oversaw technology, client relations, and technical leadership.
Compute fleet management and efficiency. $100k USD+ saved over 4 month internship.
ML-based Anomaly Detection
Internal Capacity Engineering