Senior AI Safety & Oversight Researcher

OpenAI; Los Angeles (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

A leading AI research company is seeking a Senior Researcher in AI Safety to develop models that detect and mitigate misuse and misalignment of AI systems. The ideal candidate will have over 4 years of experience in AI safety research and a Ph.D. in a related field. Responsibilities include setting research directions, improving AI safety, and collaborating with cross-functional teams to ensure products meet safety standards. Join to contribute to the responsible deployment of AGI.

Qualifications

• 4+ years of experience in AI safety.
• Experience in RLHF and large-scale AI systems.
• Strong research engineering background.

Responsibilities

• Develop AI monitor models to mitigate misuse.
• Set research directions for safer AI systems.
• Conduct research to improve reasoning about human values.

Skills

AI safety

Human-AI collaboration

Fairness & biases

Research engineering proficiency in Python

Education

Ph.D. or related degree in computer science or machine learning

Job description

A leading AI research company is seeking a Senior Researcher in AI Safety to develop models that detect and mitigate misuse and misalignment of AI systems. The ideal candidate will have over 4 years of experience in AI safety research and a Ph.D. in a related field. Responsibilities include setting research directions, improving AI safety, and collaborating with cross-functional teams to ensure products meet safety standards. Join to contribute to the responsible deployment of AGI.