Research Engineer - Data and Evaluation

Highlights

• Build tasks and environments that train Prime Intellect's models through RL.
• Design challenging evaluations for coding and long-horizon agents.
• Investigate model failures to distinguish limits from environment scoring issues.

What they offer

• Equity incentives
• Flexible work arrangements
• Visa sponsorship and relocation assistance
• Quarterly team off-sites, hackathons and conferences

Ideal candidate

A curious, ownership-driven builder fascinated by why models fail and how to measure progress. You thrive turning ambiguous quality questions into rigorous tests alongside frontier researchers.

Requirements

• Strong software engineering skills in Python and experience building data pipelines, evaluation systems, or ML workflows
• Hands-on experience working with language models or agents
• Ability to inspect complex data and model outputs and turn ambiguous quality questions into testable measurements
• Record of owning technical projects through experimentation, implementation, and validation
• Hands-on experience building technical evaluations or agent environments and debugging harness and scoring code