The Cloud Inference team is responsible for scaling and optimizing the Claude model to serve large audiences across various cloud service providers. The role involves designing and owning backend services and infrastructure that account for differences in compute hardware, networking, and operational models. Engineers in this position build automation systems for deployment and validation to ensure reliable model updates. The work includes managing capacity, optimizing costs, and routing workloads to maintain performance standards. Additionally, the role requires analyzing observability data to identify bottlenecks and collaborating with internal teams and external partners to influence provider roadmaps.

Candidates must possess significant software engineering experience with a background in high-performance, large-scale distributed systems. Proficiency in operating services on at least one major cloud platform, including experience with Kubernetes or infrastructure as code, is required. A bachelor’s degree or an equivalent combination of education, training, and experience in a relevant field is necessary. The role requires the ability to work autonomously and collaborate effectively across functional teams.