The Inference team builds and maintains critical systems that serve the Claude model to millions of users. The role involves managing the entire stack, from intelligent request routing to fleet-wide orchestration across diverse AI accelerators. Responsibilities include maximizing compute efficiency to support customer growth and providing high-performance infrastructure for research scientists. The work requires addressing complex, distributed systems challenges across multiple cloud platforms and hardware families. Staff engineers identify and resolve infrastructure blockers to ensure reliable model deployment.

Candidates must possess significant software engineering experience, specifically with distributed systems. The role requires familiarity with performance optimization, large-scale service orchestration, and intelligent request routing. A minimum of a bachelor's degree or an equivalent combination of education, training, and experience is required. Candidates should demonstrate a field of study relevant to the role through coursework or professional experience.