Model Evaluation Engineer — Benchmarks & Evals

Role overview

Remote, full-time Model Evaluation Engineer role on an AI Research team. The position centers on designing, running, and analyzing benchmarks and evaluations that measure machine learning model behavior and progress.

Responsibilities

- Design and maintain benchmark suites and evaluation methodologies - Run experiments, analyze results, and communicate findings to the AI Research team - Iterate on evaluation infrastructure to support ongoing model development

Requirements

- Experience with ML model evaluation, benchmarking, or research engineering - Strong analytical skills and rigor in experimental design - Comfort operating as part of a fully remote, distributed team