Staff+ Software Engineer, Inference Velocity

Responsibilities

• Set technical direction for Inference Developer Productivity, owning the architecture and roadmap for toolchains, dev environments, and CI/CD across GPU (CUDA), TPU, and Trainium platforms
• Be the technical owner of accelerator toolchain management: compilers, drivers, libraries, frameworks, kept current, compatible, and well-tested so Inference engineers focus on model serving instead of environment archaeology
• Design and build infrastructure for efficient accelerator usage during development, including devbox environments, pre- and post-land validation automation, and shared tooling that reduces the cost of working across heterogeneous hardware
• Define and instrument productivity metrics for the Inference org, building the dashboards and alerting that surface regressions early (smoke tests red for extended periods, build times creeping up, toolchain breakages) and drive them to resolution
• Proactively hunt down bottlenecks, toil, and friction across Inference engineering workflows, then design and build the systems that eliminate them
• Act as the technical counterpart to Anthropic's central Infrastructure org, aligning on shared developer productivity initiatives, contributing Inference-specific 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

Languages