Research Engineer, Reward Models Platform

We are seeking a Research Engineer to design and build infrastructure that enables researchers to rapidly iterate on reward signals, including tools for rubric development, human feedback data analysis, and reward robustness evaluation.

Requirements

• Design and build infrastructure that enables researchers to rapidly iterate on reward signals
• Develop systems for automated quality assessment of rewards
• Create tooling that allows researchers to easily compare different reward methodologies
• Build pipelines and workflows that reduce toil in reward development
• Implement monitoring and observability systems to track reward signal quality

Benefits

• Competitive compensation
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space