Global AI MapJOBS / OpenAI
Researcher, Safety Training
San Francisco; London, UK
Role
The role involves developing safety training methods for OpenAI models, including RLHF, DPO, and PPO, to improve alignment and reliability. Candidates must have hands-on experience with post-training methods and hold a PhD or equivalent practical research experience.
Location: San Francisco; London, UK
Employment: unspecified
Work pattern: unspecified
Seniority: unspecified
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2023-05-25T04:06:29.356+00:00. Check the employer’s page for the complete description, current availability and application terms.