About the job

Anthropic is hiring a Staff Software Engineer for its Inference team to build and maintain large-scale systems that serve AI models to millions of users globally. The role involves designing and optimizing distributed systems, managing intelligent request routing, orchestrating compute resources across multiple cloud platforms and AI accelerators, and improving performance and scalability of inference infrastructure. Candidates will work across the full stack to solve complex engineering challenges related to high-performance computing, load balancing, and real-time model serving. Ideal applicants have extensive experience in distributed systems, cloud infrastructure, and performance optimization, along with strong programming skills in languages such as Python or Rust. This is a highly senior and impactful technical role in a leading AI company offering competitive compensation and visa sponsorship for eligible candidates.