Senior AI Engineer

Role overview A senior engineering role on a team building the tracing, evaluation, and observability platform that thousands of developers rely on to monitor, debug, and optimize LLM, RAG, and multi-agent systems. The work sits at the research–product boundary: pushing forward agent evaluation, LLM-as-judge techniques, and autonomous optimization, then shipping those advances as features engineers use every day. The bar is deliberately high, and the team hires only experienced senior AI engineers.

Responsibilities - Design and ship features across tracing, evaluation, and observability for AI agents running in production - Drive research on agent evaluation, LLM-as-judge methodologies, and autonomous optimization, and convert findings into product - Deploy AI models in production and instrument their behavior for deep analysis - Build tools that help developers debug, monitor, and improve LLM, RAG, and multi-agent systems

Requirements - 2–3+ years of experience building AI agents extensively - A track record of deploying AI models in production - Hands-on experience analyzing and evaluating how LLM, RAG, or multi-agent systems behave