Frontier AI Evaluation Scientist

Neura Market; San Francisco (CA); On-site; USD 200,000 - 250,000; Full time

Job summary

OpenAI is seeking a researcher to advance frontier evaluations and environments for safe AGI/ASI. You will help design north star model environments and steer major training runs so that research outputs translate into real-world products.

Collaborate with researchers, engineers, product and safety teams to decide what to measure, how to measure it, and how to ship improvements. This high-autonomy role rewards curiosity and clear communication.

Qualifications

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, model training, coding agents, tool-using agents, or production ML systems.
• Interested in open-ended problems requiring research taste and engineering execution.

Responsibilities

• Create ambitious RL environments to push frontier model capabilities and measure behaviors.
• Develop new methodologies for automatically exploring model behavior.
• Dive into measurement science, including scalability, reliability, and variance of evaluation.
• Help steer training for the largest runs and translate insights into improvements.
• Design scalable systems to support continuous evaluation.
• Build self-improvement loops to automate model understanding.

Skills

ML fundamentals

Software engineering

RL & evaluation

Job description

OpenAI is seeking a researcher to advance frontier evaluations and environments for safe AGI/ASI. You will help design north star model environments and steer major training runs so that research outputs translate into real-world products.

Collaborate with researchers, engineers, product and safety teams to decide what to measure, how to measure it, and how to ship improvements. This high-autonomy role rewards curiosity and clear communication.