Research Scientist, AI Evaluation Science

What you'll do

• Advance evaluation methodology through original research in areas like preference learning and reward modeling.
• Publish findings at top-tier venues to contribute to the recognition of evaluation science.
• Translate complex methods into production-ready tools by partnering with platform engineers.
• Collaborate with measurement scientists to integrate psychometric methods into evaluation systems.
• Define the team's research agenda by identifying high-leverage open problems in evaluation science.

What we're looking for

• Ph.D. in Computer Science, Machine Learning, or related field with focus on evaluation-adjacent areas.
• Strong publication record at top-tier conferences like NeurIPS, ICML, ICLR, ACL, EMNLP.
• Deep expertise in preference learning, reward modeling, calibration theory, or human-AI interaction methodology.
• Ability to implement complex methods from recent papers and run large-scale experiments.
• Track record of translating research into practical systems used by others.
• Excellent written and verbal communication skills for diverse audiences.