← All roles

Performance Engineer, Inference Engine

Anthropic· AI Research & Engineering
Apply on company site
Hybrid (San Francisco, CA / New York City, NY)$350k - $850kFull-timePosted 1mo ago

About the role

Performance Engineer role focused on building and optimizing Anthropic's inference engine across accelerator and cloud platforms, improving throughput, cost, reliability, and latency while ensuring safety and model quality.

Responsibilities

  • Keep device utilization high. Accelerators should never be waiting due to other overheads.
  • Reuse instead of recompute. Keep model state cached and reuse it whenever cheaper than computing anew.
  • Measure, model, then change. Build observability, model impact of improvements, deploy and iterate to speed up Claude.
  • Tokens you can trust. Ensure model quality remains across platforms and over time.
  • Safety on every token. Work with safeguards and safety teams; inference engine supports production safety systems.

Qualifications

  • A working mental model of LLM inference: how prefill and decode land on an accelerator's compute, memory, and interconnect, and what the host is doing meanwhile
  • Proven quick learner: ramped fast in deep, unfamiliar systems and shipped consequential changes quickly
  • Strong systems programming (Rust, C++, or similar), with care for code quality and tests
  • Analytical about performance: observe and profile first, form a hypothesis, test it, then change the code and measure again
  • Low ego: ask naive questions, take feedback well, pick up slack outside job description
  • Enjoy pair programming and care about societal impacts of work

Skills

Required:LLM inferenceSystems programmingPerformance analysisHardware/accelerator familiarityPair programming

Benefits

  • Competitive compensation and benefits
  • Optional equity donation matching
  • Generous vacation and parental leave
  • Flexible working hours
  • Lovely office space
Last updated Sep 16, 2026. Interested? Apply on the company site.

About Anthropic

building reliable, interpretable, and steerable AI systems

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

ai-infrastructure-and-developmentliquid-ai-recruiting-targetsetter-30setter-30-2026-q1wing-list-2026wing-list-2026-giga-stage
Company profileWebsite

More open roles at Anthropic