Product Designer, Evals & Prompts

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, engineers, policy experts, and business leaders working together to build beneficial AI systems.

Prompts spec out what Claude does. Evals measure whether it did. The Product Prompt and Eval Design team does both for product design: the system prompt that greets a new user, the tool descriptions that decide whether Claude searches, the instructions that keep a slide deck from tipping into slop, and the evals that test all of it. The point is to keep the model and the product aligned with what users expect, what the product strategy calls for, and what safety requires, on every surface and through every model launch.

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.

• 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

• 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

• 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

<div