jobs

Product Designer, Evals & Prompts

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

Status

Open

Posted

2026-09-04T23:15:58+00:00

Anthropic's Product Prompt and Eval Design team writes the prompts behind Claude's tools and features and the evals that check them. This hire works the eval side: authoring graders and rubrics, scaling a harness that exercises 50 to 100 tools across models, and building low-code eval tools designers can run without an engineer. The posting wants production-quality Python, experience maintaining LLM evaluation pipelines — graders, comparison sets, regression suites — and a habit of reading transcripts, not only scores. Model-release support runs throughout.