Staff+ Software Engineer, Inference Runtime

Anthropic · Remote

Posted
2 days ago
Last confirmed live
Today

What this role involves

Anthropic seeks a Staff+ Software Engineer to lead the Inference Runtime team, owning the architecture and roadmap for the shared, accelerator-agnostic inference serving stack. The role involves hands-on work in Rust and Python, driving efficient accelerator usage across GPU, TPU, and Trainium, and setting technical direction for validation and release systems.

Skills this posting asks for

  • systems engineering
  • ml infrastructure
  • rust
  • python
  • cuda
  • gpu
  • tpu
  • trainium
  • aws neuron
  • performance profiling
  • latency optimization
  • throughput optimization
  • distributed systems
  • compilers
  • build systems
  • toolchains
  • slos
  • canary testing
  • shadow testing
  • rollback

Requirements

  • Level: staff

From the employer’s posting

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, en…

Read the full description on Anthropic’s careers page

Apply without filling the form

Approve this role and the application is completed for you, including a résumé tailored to it. You get a confirmation when it lands, and a credit is only spent when a submission is confirmed.

Other roles at Anthropic

All 142 roles at Anthropic