Machine Learning Researcher

• Conduct AI safety research to identify and defend against failure modes in advanced AI systems.
• Discover emerging failure modes through stress-testing cutting-edge AI models.
• Help enterprises deploy AI safely and at scale without compromising innovation.
• Inform official safety evaluations of the world's most advanced AI models.

This role directly contributes to the safe deployment of advanced AI systems, helping to prevent catastrophic failures and ensuring AI benefits society.

• Strong background in machine learning and AI safety research.
• Experience with stress-testing or evaluating AI models.
• Ability to develop research-backed solutions for emerging challenges.

Compensation and benefits are not specified in the posting.

Gray Swan is an organization focused on AI safety, working to identify and defend against failure modes in advanced AI systems.