jobs

Researcher, Robustness & Safety Training

About the TeamThe Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society and is at the forefront of OpenAI's mission to build and deploy safe AGI,

Company

OpenAI

Location

San Francisco; London, UK

Status

Open

Posted

2023-05-25T04:06:29.356+00:00

OpenAI's Safety Systems team, within Model Safety Research, seeks a senior researcher to advance safety methods. The person sets research directions and runs projects on RLHF, adversarial training and robustness, implements new methods in core model training, launches safety improvements in products, evaluates model safety and proposes mitigations, and works with trust and safety, legal, policy and other researchers. The posting asks for 4+ years in AI safety, safety work for model deployment, a PhD or related degree in computer science or machine learning, and deep learning or engineering strength.