Research Engineer, Frontier Evals & Environments

Builds ambitious RL environments and evaluation systems to measure and steer frontier AI models toward safe AGI. Requires strong ML research engineering, statistical skills, and red-teaming mindset for end-to-end project ownership in fast-paced setting.

About the job

Responsibilities

Create ambitious RL environments to push our models to their limits
Work on measuring frontier model capabilities, skills, and behaviors
Develop new methodologies for automatically exploring the behavior of these models
Help steer training for our largest training runs, and see the future first
Design scalable systems and processes to support continuous evaluation
Build self-improvement loops to automate model understanding

Requirements

Passionate and knowledgeable about AGI/ASI measurement
Strong engineering and statistical analysis skills
Able to think outside the box and have a robust “red-teaming mindset”
Experienced in ML research engineering, stochastic systems, observability and monitoring, LLM-enabled applications, and/or another technical domain applicable to AI evaluations
Able to operate effectively in a dynamic and extremely fast-paced research environment as well as scope and deliver projects end-to-end

Nice-to-haves

First-hand experience in red-teaming systems—be it computer systems or otherwise
An ability to work cross-functionally
Excellent communication skills

Skills

Reinforcement Learning, Machine Learning, LLMs, Statistical Analysis, Red-Teaming, Observability, Monitoring, Stochastic Systems, Rl Environments, Model Evaluation