Staff+ Software Engineer, Inference Runtime

ABOUT THE ROLE We are seeking a highly skilled Staff+ Software Engineer to lead our Inference Runtime team at Anthropic. As a technical lead, you will be responsible for setting the technical direction for the shared runtime of our inference serving stack, ensuring its performance, correctness, and abstractions across various accelerator platforms. You will partner with cross-functional teams to drive efficient accelerator usage, build robust validation surfaces, and mentor engineers on the team. WHAT YOU'LL DO - Set technical direction for the team, owning the architecture and roadmap for the shared runtime of the inference serving stack - Own and evolve the accelerator-agnostic runtime itself, including hands-on work in a performance-sensitive Rust and Python codebase - Drive efficient accelerator usage across GPU, TPU, and Trainium - Build the runtime's validation surface around partitioned builds, change-scoped testing, and canary/shadow/rollback as first-class mechanisms - Act as a technical counterpart to Anthropic's central Infrastructure org on compilers, build systems, and toolchains - Mentor engineers on the team through design review, code review, and direct collaboration WHAT YOU'LL NEED - Deep background in systems engineering or ML infrastructure, with hands-on experience with performance profiling, latency and throughput optimization, and systems debugging at scale - Real depth in at least one accelerator ecosystem (CUDA/GPU, TPU, or Trainium/AWS Neuron) and genuine appetite to keep the runtime agnostic across all of them - Significant software engineering experience, with a strong background in high-performance, large-scale distributed systems serving millions of users - A track record of defining and using engineering metrics to drive improvement - Experience driving technical alignment across organizational boundaries - Strong written and verbal communication, and the ability to influence technical direction without formal authority WHY REMOTE As a remote employee at Anthropic, you will have the flexibility to work from anywhere and be part of a team that is shaping the future of AI. You will have the opportunity to work on complex technical problems, collaborate with talented engineers, and contribute to the development of our inference serving stack. BENEFITS - Annual compensation range: $405,000 - $485,000 USD - Comprehensive health plan - Parental leave - Education stipend - Life insurance - Flexible schedule