jobs

Performance Engineer, Inference Engine

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

Status

Open

Posted

2026-09-09T23:09:53+00:00

Anthropic is hiring a Performance Engineer for its Inference Engine, the in-house software between accelerator kernels and routing. The role focuses on optimizing throughput, cost, reliability, and latency across accelerator and cloud platforms, including batching, memory, model layout, and distributed coordination. The posting seeks strong systems programming in Rust or C++, LLM inference knowledge, and performance profiling. Preferred experience includes GPU programming, OS internals, transformers, and schedulers or caches. Work is deeply technical and collaborative, with pair programming emphasized.