Researcher, Safety Oversight

OpenAI · San Francisco, United States · Full-time

Team: Research

Posted: 2025-01-28

Pay: USD 380000 – USD 500000 per year

The Researcher, Safety Oversight, will lead research initiatives to develop methods for identifying and mitigating AI misuse and misalignment while ensuring the robustness of frontier AI models. The role requires a Ph.D. or equivalent degree, at least four years of experience in AI safety research, and proficiency in Python to design oversight systems and red-teaming pipelines.

Skills & tags: ai safety, machine learning, python, rlhf, human-ai collaboration, red teaming, model alignment, robustness, scalable oversight, fairness and bias

View and apply at the original posting

Postings belong to their employers; this page links to the source.

JOB DETAILS

Job details