jobs
Performance Engineer, Inference Systems
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,
- Company
- Anthropic
- Location
- San Francisco, CA; New York City, NY; Seattle, WA
- Status
- Open
- Posted
- 2026-05-20T22:53:11+00:00
Anthropic's Inference System Dynamics team is hiring a performance engineer to study the whole stack that serves Claude — accelerator kernels, model servers, routing, autoscaling, capacity — against throughput, latency, reliability, and correctness targets. The work mixes tracing latency regressions and modeling compute funnels with owning the correctness evaluation pipeline that flags output regressions. The posting wants profiling and roofline experience, Python, and SQL-or-pandas analysis; it prefers GPU/TPU performance knowledge and large-scale inference background. The role influences other teams rather than owning components.
Original job posting