Research Engineer, Reward Models Platform

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. Develop automated quality assessment of rewards, including detection of reward hacks and other pathologies. Create tooling that allows researchers to compare different reward methodologies (preference models, rubrics, programmatic rewards) and understand their effects. Build pipelines and workflows that reduce toil in reward development, from dataset preparation to evaluation to deployment. Implement monitoring and observability systems to track reward signal quality and surface issues during training runs. Collaborate with researchers to translate scientific requirements into platform capabilities, optimize for performance, reliability, and ease of use, and contribute to best practices and documentation.