Director, Research - AI Evals

Figma•San Francisco, NY

8d•Hybrid

About The Position

Figma is growing its team of passionate creatives and builders on a mission to make design accessible to all. Figma’s platform helps teams bring ideas to life—whether you're brainstorming, creating a prototype, translating designs into code, or iterating with AI. From idea to product, Figma empowers teams to streamline workflows, move faster, and work together in real time from anywhere in the world. The Figma Research team is hiring an Director, Research - AI Evals to own how we measure the quality of Figma's AI-powered experiences. As Figma ships more AI capabilities across our products, the question "is this really good?" has never mattered more — and answering it rigorously is what this role exists to do. You'll define what "good" means for our AI features, build the frameworks and quality bars to measure it, and turn that into trusted signal that product teams rely on to decide what to ship. The ideal candidate brings deep, hands-on experience evaluating AI/LLM-powered products — blending human evaluation with automated, model-based approaches — along with the product instinct and communication skills to make evaluation genuinely useful. Partnering with Product, Design, Engineering, and Data Science, you'll sit upstream of nearly every AI shipping decision at Figma and directly shape the quality of features used by millions of people. This is a full time role that can be held from one of our US hubs or remotely in the United States.

Requirements

10+ years of experience in product, research, applied research, or a closely related field, including 2+ years of management experience
Direct, hands-on experience owning the evaluation of AI/LLM-powered products
Expertise designing and running AI evaluation — human evaluation programs, rubric and benchmark/golden-dataset construction, inter-rater reliability — and sound judgment about when and how to apply automated/model-based approaches (e.g., LLM-as-judge), including their limitations
Strength across both qualitative and quantitative methods, comfort with data and metrics, and the ability to reason about model behavior
Demonstrated success in identifying the riskiest assumptions behind an ambiguous quality question, prioritizing them, and designing right-sized evaluation to build confidence
A proven track record of gaining buy-in from executive and cross-disciplinary stakeholders — transcending methodology to articulate a larger user story and the "so what" to inspire action

Nice To Haves

Experience building or co-building automated evaluation pipelines and regression testing in partnership with engineering, or familiarity with eval tooling (e.g., Braintrust, LangSmith, DeepEval, or equivalents)
Experience standing up a new function, practice, or discipline from scratch
2+ years in product design, user-centric product management, data science, product development, and/or front-end engineering
A familiarity and depth of experience using Figma's products

Responsibilities

Own AI evaluation methods and operations for Figma's AI-powered experiences — define quality dimensions, design how we measure them, and turn results into decision-ready signal
Build and maintain evaluation frameworks, rubrics, golden datasets, and quality bars, combining human evaluation with automated/model-based approaches (e.g., LLM-as-judge) where appropriate
Partner with engineering to stand up repeatable, reproducible evaluation pipelines and regression testing, so evaluation is a routine part of how AI features are built and shipped
Produce clear readouts and dashboards that let stakeholders confidently make go/no-go and prioritization decisions
Socialize a shared definition of quality so evaluation standards are adopted across teams rather than re-invented — and advocate for evaluation as a strategic partner in the product process
Manage a small team to execute our AI evals in partnership with contractors, internal staff, and/or LLMs