Frontier AI Evaluation & Environments Researcher

OpenAI; California (MO); On-site; USD 180,000 - 230,000; Full time

Job summary

OpenAI is hiring a researcher for Frontier Evals & Environments to build north star model environments and guide research programs behind their frontier models. You will work with researchers, engineers, product, infrastructure, and safety teams to decide what goes into major model runs, measure success, and ship improvements for real-world use.

You will thrive if you have strong ML and systems fundamentals, hands-on experience with LLMs and RL, and enjoy turning vague problems into concrete

Qualifications

• Strong technical fundamentals in machine learning, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, or production ML systems.
• Ability to design scalable evaluation environments and run rigorous experiments (high-agency role).

Responsibilities

• Create ambitious RL environments to push frontier models and measure capabilities, skills, and behaviors.
• Develop new methodologies for automatically exploring model behavior.
• Dive into measurement science, including scalability, reliability, and variance of evaluations.
• Help steer training for large-scale runs and ship improvements into products.

Skills

Machine Learning

Software Engineering

Systems

Statistics

Research

Tools

Python

ML Frameworks

Evaluation Tools

Job description

OpenAI is hiring a researcher for Frontier Evals & Environments to build north star model environments and guide research programs behind their frontier models. You will work with researchers, engineers, product, infrastructure, and safety teams to decide what goes into major model runs, measure success, and ship improvements for real-world use.

You will thrive if you have strong ML and systems fundamentals, hands-on experience with LLMs and RL, and enjoy turning vague problems into concrete