Research Engineer, Data & Evals

Building synthetic data pipelines and evaluation systems, the full-time Research Engineer, Data & Evals will design and maintain benchmarks for legal workflows while collaborating with legal experts to enhance model performance in a remote environment.

Key responsibilities

Develop synthetic data pipelines for training and evaluation of legal reasoning models
Design and calibrate evaluations that reflect real legal work, ensuring alignment with expert judgment
Collaborate with researchers to analyze model failures and improve training based on customer feedback

Required qualifications

Experience in building data pipelines, ML evaluation systems, or experimentation tooling with strong Python skills
Understanding of statistical reasoning and experimental design for accurate measurement
Ability to convert ambiguous goals into structured datasets and measurable criteria
Familiarity with synthetic data, LLM evaluations, or automated raters is a plus
Strong background in data and measurement engineering related to ML model development