Research Engineer / Scientist, Data & Evals

Highlights

• Build synthetic data pipelines for complex legal reasoning and agentic workflows.
• Design evaluations and benchmarks like Legal Agent Benchmark for real legal work.
• Turn expert feedback and product usage into training signals that improve models.

Ideal candidate

A rigorous, hands-on builder who obsesses over measurement and data quality. You love turning ambiguous expert judgment into clear signals and partnering closely to turn model failures into real gains.

Requirements

• Experience building data pipelines, ML evaluation systems, or experimentation tooling
• Strong Python skills with ownership of production-quality code
• Rigorous approach to measurement including statistical reasoning and experimental design
• Ability to translate ambiguous goals or expert judgment into structured datasets, rubrics and measurable criteria