Research Engineer - Eval Platform

The Role

Evaluation is how we decide which models, checkpoints and recipes ship. As a Research Engineer on the Eval Platform team, you will build the infrastructure every science team relies on to measure model quality, and make it reliable, reproducible and fast.

You don't need to have designed benchmarks before. You do need to care about what a score means, and about when a difference between two runs is real.

What you will do

• Build systems that keep eval results reproducible and comparable over time, as models, benchmarks and code evolve.

• Run evaluations at scale across our GPU clusters, from model serving to scoring.

• Make eval results easy to access, explore and trust, through APIs and dashboards that researchers use every day.

• Catch broken or noisy evals before they mislead research decisions.

• Support evaluation of agentic, multi-turn and tool-using models.

• Work closely with researchers to turn new evaluation needs into robust, shared tooling.

• Master's or PhD in Computer Science, or equivalent experience.

• 4+ years building production-grade software, ideally large-scale ML codebases or distributed systems.

• Excellent Python and strong software-design instincts: testing, code review, CI/CD.

• Experience running workloads on GPU clusters (Slurm, Kubernetes, Ray or similar).

• Familiarity with LLM inference and evaluation.

• A product mindset: researchers are your users.

• Self-starter, low-ego, collaborative.

Nice to have

• Experience building or maintaining evaluation harnesses or benchmarks.

• Hands-on experience with inference engines such as vLLM or SGLang.

• Experience with agentic or RL environments.

• Statistics for experimentation: variance estimation, significance testing.

• Open-source contributions to ML tooling.