Research Engineer: Frontier Evals & Environments

Research Engineer, Frontier Evals & Environments; San Francisco (CA); On-site; USD 180,000 - 300,000; Full time

Job summary

OpenAI is seeking a researcher for Frontier Evals & Environments to help create north star model environments that push capabilities while guiding safe AGI progress. You’ll collaborate with researchers, engineers, product teams, infrastructure, and safety partners to decide what to include in major model runs, measure outcomes, and ship improvements to products used by real people.

You will work in a high-autonomy role where your work directly influences frontier models and their real-world

Qualifications

• Strong ML fundamentals and ability to learn quickly across domains.
• Hands-on experience with LLMs, RL, post-training evals, or production ML systems.
• Interest in open-ended problems where the path is unclear and the signal is noisy.
• Focus on product impact and model behavior, not just benchmark movement.

Responsibilities

• Create ambitious RL environments to push our models to their limits and measure frontier model capabilities, skills, and behaviors.
• Develop new methodologies for automatically exploring the behavior of these models.
• Dive deep into the science of measurement, including understanding scalability, reliability, and variance of evaluation.
• 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.

Skills

ML fundamentals

Software engineering

Statistics

LLMs

RL

RLHF/RLAIF

Evaluation methods

Architecting ML systems

Post-training

Coding agents

Tool-using agents

Production ML systems

Job description

OpenAI is seeking a researcher for Frontier Evals & Environments to help create north star model environments that push capabilities while guiding safe AGI progress. You’ll collaborate with researchers, engineers, product teams, infrastructure, and safety partners to decide what to include in major model runs, measure outcomes, and ship improvements to products used by real people.

You will work in a high-autonomy role where your work directly influences frontier models and their real-world