Research Engineer, Frontier Safety Risk Assessment
Google DeepMind · Added 2 days ago
Applications are handled by the employer or external application platform. AI Safety Careers does not process applications directly.
San Francisco Bay Area
$136,000 - $245,000
In this role, you'll design and validate approaches to assess and mitigate catastrophic risks from frontier AI systems.
Identify new risk pathways within areas like loss of control, ML R&D, cyber, and harmful manipulation.
Develop innovative measurement techniques for pre-mitigation and post-mitigation AI risks.
Forecast and create scenario plans for future AI risks not yet material.
Apply conceptual thinking and Python engineering to prioritize efforts based on information value.
Google DeepMind is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Google DeepMind that we think may be high impact. We do not necessarily recommend working at other positions at Google DeepMind. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.
This listing may be aggregated from a public source or submitted by a third party. If you represent this employer and would like to update or remove this listing, contact support@aisafetycareers.com.