We’re hiring a Researcher, AI Evaluations to join AI Insights within Figma’s Research team. This is a senior individual contributor role with no direct reports, reporting to the AI Insights lead and working directly with AI Research within AI Platform. You’ll strengthen the team’s model, agent system, and evaluation work through hands-on studies, clear rubrics, and reliable measures of quality that reflect user needs, and your findings will guide model and product improvements.

This is a full time role that can be held from one of our US hubs or remotely in the United States.

What you’ll do at Figma:

• Own evaluation research for priority AI Research workstreams. Define quality criteria, design studies, analyze results, and recommend actions
• Build rubrics, representative evaluation datasets, benchmarks, and quality thresholds that reflect user needs and expert design judgment
• Work with AI Research and Modeling Platform engineers to integrate validated methods into repeatable evaluations and regression tests
• Explain quality, failure patterns, and uncertainty. Recommend actions that guide model selection, model improvements, product priorities, and release decisions
• Validate automated graders against human ratings, including LLM-as-judge methods that use a large language model to score outputs. Identify bias, gaps, and uncertainty
• Connect user research with AI Research’s model development work. Share reusable methods, review work, and mentor peers

We’d love to hear from you if you have:

• 7+ years of experience in research, applied research, or a related field, with a proven track record of independently leading complex evaluation projects and delivering measurable impact
• Hands-on experience evaluating AI products, with demonstrated ability to translate evaluation findings into meaningful model and product improvements
• Expertise in designing human evaluations, scoring rubrics, datasets, and benchmarks, including measuring inter-rater agreement and validating automated graders
• Strong qualitative and quantitative research skills, with the ability to analyze data, interpret uncertainty, and draw actionable insights into model behavior and performance
• Excellent problem-solving and stakeholder management skills, with the ability to navigate ambiguity, prioritize risks, balance speed with rigor, and deliver recommendations that influence cross-functional decisions

While it’s not required, it’s an added plus if you also have:

• Experience integrating automated evaluations and regression testing into engineering workflows, with familiarity in tools such as Braintrust, LangSmith, DeepEval, or equivalent platforms
• Proven ability to develop scalable, reusable evaluation frameworks and drive the adoption of consistent quality standards across teams
• Background in product design, product management, data science, or engineering, with familiarity in Figma or similar design and developer tools
• Strong statistical expertise in sampling, significance testing, and agreement metrics, with experience conducting experiments or analyzing performance metrics for AI-powered features
• Advanced training in a quantitative or behavioral discipline, gained through formal education or equivalent hands-on experience