Senior Backend AI Engineer — Production-Scale LLM Systems
Summary
Senior AI engineer in San Francisco builds and scales low-latency backend systems for LLM-powered features on AWS, ensuring performance and observability.
Zep AI (YC W24) is seeking a Senior AI Engineer in San Francisco to build low-latency backend systems. This role involves shipping LLM-powered features, operating systems at scale on AWS, and ensuring quality across performance and observability. Candidates should have 6+ years of experience in production engineering, a Master's in Computer Science, and hands-on experience in AI agents and LLM applications. Nice to have TypeScript knowledge. Join a small, collaborative team focused on impactful problem-solving.
