AT A GLANCE
Staff Engineer leading the accelerator-agnostic inference runtime platform serving Claude to millions of users, owning architecture, performance, and cross-team technical alignment.
KEY SKILLS
RustPythonCUDAGPU optimizationTPUAWS Neuron/TrainiumDistributed systemsPerformance profilingML inferenceKubernetesCI/CD systemsXLATritonSystems debugging
WHAT YOU'LL DO
- Set technical direction and architecture for the shared inference runtime serving stack
- Own and evolve the accelerator-agnostic runtime interfaces, internal boundaries, and build structure
- Drive efficient accelerator usage across GPU, TPU, and Trainium platforms
- Build validation systems around partitioned builds, change-scoped testing, and canary/shadow/rollback mechanisms
- Ensure new models and deployment targets pay only for their own specialization
- Act as technical counterpart to Infrastructure org on compilers, build systems, and toolchains
- Mentor engineers through design review, code review, and direct collaboration
- Drive technical alignment across organizational boundaries on serving, scaling, and accelerator teams