Research Engineer, Frontier Evals & Environments
Research Engineer, Frontier Evals & Environments
Research Engineer, Frontier Evals & Environments
OpenAI
The Research Engineer role at OpenAI's Frontier Evals & Environments team focuses on developing and evaluating advanced AI models to ensure safe AGI/ASI. The team is dedicated to creating innovative environments for model training and evaluation, contributing to the advancement of AI capabilities. Candidates should possess strong engineering and analytical skills, with a passion for AI measurement and the ability to work in a fast-paced research environment.
Qualification
- Passionate about AGI/ASI measurement
- Strong engineering and statistical analysis skills
- Ability to think outside the box with a red-teaming mindset
- Experience in ML research engineering or stochastic systems
- Ability to operate in a fast-paced research environment
Responsibility
- Create ambitious RL environments to push models to their limits
- Measure frontier model capabilities, skills, and behaviors
- Develop methodologies for exploring model behavior
- Steer training for large model training runs
- Design scalable systems for continuous evaluation
- Build self-improvement loops for model understanding
