Fellows, AI Safety and Security

• In this fellowship, you'll conduct a 4-month full-time empirical research project on AI safety or security aligned with Anthropic's priorities.
• Work under direct mentorship from Anthropic researchers in areas such as scalable oversight or mechanistic interpretability.
• Produce a public research output such as a paper submission from your empirical project.
• Develop and test approaches to technical problems in AI safety or security using external resources.
• Iterate rapidly on your research ideas based on mentor feedback and research outcomes.

Anthropic is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Anthropic that we think may be high impact. We do not necessarily recommend working at other positions at Anthropic. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.