Product Designer, Evals & Prompts

The shape of it

In the posting’s own words

This role is a foundational member of that work on the eval side: building the evals that check the prompts, the harness that runs them, and the tools that let designers do this work themselves. It sits on the Product Prompt and Eval Design team in Product Design, works day to day with the team's surface owners and the engineers in each product team, and pairs per surface with the prompt engineering team at model releases.

What it asks for · 6

• Production-quality Python
• Experience building and maintaining evaluation pipelines for LLM products: graders, rubrics, comparison sets, regression suites, and the plumbing that runs them across models
• Experience building internal tools with a real interface for people who do not write code
• Experience standing up test harnesses, sandboxing tool calls, and pinning the settings that make runs comparable
• Experience shipping prompts, or working closely with people who do, and understanding why a prompt that works on one model fails on the next
• Reads transcripts, not only scores

Also a plus

• Has worked inside a model-launch cycle
• A/B testing experience and the ability to connect offline evals to online outcomes
• Front-end or notebook-to-app experience, and opinions about what makes an eval result legible at a glance
• Has turned product rubrics into training signal: graders, human-feedback questions, or preference pairs
• Cares how Claude behaves for the people using it, not only whether the metric moved

What the job covers

• Write and revise the prompts behind Claude's tools, features, and behaviors on a product surface; test the surface, turn findings into prompt fixes, ship them, and confirm the prompt users get is the one intended
• Build the graders that prove a prompt fix and rerun on the next model; turn designers' hand-run rubrics into automated evals, then read transcripts for what the eval missed
• Build visual, low-code eval tools designers can use without an engineer: assemble a comparison set from real transcripts, turn a plain-English rubric into a grader, compare prompt variants across models side by side, and read results in the tool rather than a notebook
• Watch designers use those tools and make them simpler
• Support model releases: test each surface against the new model, write prompt fixes and migrations, and write prompts for features launching with it, so the surface owner's call has numbers behind it
• Stand up and scale the eval harness: build the test environment that exercises our 50 to 100 tools with trustworthy settings, keep evals green across models, and call whether a regression is the harness or the model
• Package what prompting can't fix for training, with the eval attached: graders for crisp behaviors, human-feedback questions and good/bad pairs for fuzzy ones like writing quality

Tools and skills named

Words the posting leans on

• prompt15×
• eval14×
• model11×
• product10×
• tools9×
• surface7×
• experience6×
• graders5×
• test5×
• call4×
• claude4×
• design4×
• designers4×
• rubrics4×
• whether4×
• write4×

Counted from the posting after the mission statement and the legal notices are set aside. The ones near the top are the ones a screener is looking for.

More open at Anthropic

• Account Executive, AI NativeNew York City, NY; San Francisco, CA | New York City, NY
• Account Executive - DNBSingapore
• Account Executive - Public Sector (ASEAN)Singapore
• Account Executive, StartupsSan Francisco, CA | New York City, NY
• Accounting, Revenue Internal ControlsSan Francisco, CA | Seattle, WA
• Administrative Business Partner, GTMSan Francisco, CA