The role involves building and maintaining critical systems that serve AI models to millions of users globally. Responsibilities include managing the entire stack from intelligent request routing to fleet-wide orchestration across diverse hardware accelerators. The team focuses on maximizing compute efficiency to support customer growth while providing high-performance infrastructure for research. Projects include designing routing algorithms, autoscaling compute fleets, and building production-grade deployment pipelines. The work also entails integrating new accelerator platforms and analyzing observability data to optimize performance.

Candidates must possess significant software engineering experience, with a specific focus on distributed systems. A bachelor’s degree or an equivalent combination of education, training, and experience in a relevant field is required. The role demands a results-oriented mindset with a focus on flexibility and impact. Additionally, the ability to contribute to technical excellence and an interest in the societal impacts of AI systems are necessary.