Research Engineer - Data and Evaluation

Description: Build tasks and environments for training Prime Intellect’s models through reinforcement learning (RL) and evaluations. Collaborate with researchers to investigate model failures and improve task implementations and scoring. Requirements: Strong software engineering skills in Python; experience with data pipelines, evaluation systems, or ML workflows. Hands-on experience with language models or agents; understanding of training data and evaluation impacts on model behavior. Ability to analyze complex data and model outputs to identify failure modes and create testable measurements. Proven track record of managing technical projects through experimentation and collaboration with researchers. Experience in building evaluations or agent environments, with skills in debugging model traces and scoring code. Benefits: Cash compensation range of $150-350k, including equity incentives. Flexible work arrangements, with options for remote or in-person work in San Francisco. Visa sponsorship and relocation assistance for international candidates. Quarterly team off-sites, hackathons, and learning opportunities. Work with a talented, mission-driven team passionate about advancing technology in AI.