Staff+ Software Engineer, Inference Runtime

Anthropic seeks a Staff+ Software Engineer for Inference Runtime to lead technical direction for the accelerator-agnostic core of their inference serving stack. The role involves hands-on work in Rust and Python, driving efficient accelerator usage across GPU, TPU, and Trainium, and building validation systems. Ideal candidates have deep systems engineering or ML infrastructure background with expertise in at least one accelerator ecosystem.

• 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 – its interfaces, internal boundaries, and build structure – including hands‑on work in a performance‑sensitive Rust and Python codebase - Keep the platform's expansion cost low by ensuring new models and deployment targets pay only for their own specialization, and edge cases stitch back into the core easily - Drive efficient accelerator usage – utilization, scheduling, memory management – 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 the compilers, build systems, and toolchains the runtime depends on, contributing Inference's performance and correctness requirements, and making the call on build vs. adopt - Mentor engineers on the team through design review, code review, and direct collaboration, raising the technical bar without owning headcount