Researcher, Evals

📋 Description

• Identify and define key model capabilities for next-gen evals
• Develop evaluation pipelines with robust stats and clear reporting
• Embed evaluation systems into model development loops with teams
• Prototype user studies and behavioral experiments for real-world use

🎯 Requirements

• Experience designing evaluation frameworks for generative models (audio, text, multimodal)
• Strong technical and analytical skills to translate ideas into production-ready systems
• Creativity in defining quantitative metrics for subjective quality
• Excitement for building eval systems bridging research and real-world use
• Curiosity and rigor to measure meaningful progress in intelligent behavior

🎁 Benefits

• Health insurance, dental and vision coverage
• 9 weeks paternity and 12 weeks maternity leave
• 401(k) retirement plan
• Commuter allowance
• Flexible PTO
• Meals and snacks provided