AI Security Fellow

• In this fellowship, you'll conduct AI security research for four months, working to identify and address potential risks from advanced AI systems while producing publishable outputs.
• Develop empirical projects using external infrastructure like open-source models and public APIs.
• Collaborate with Anthropic researchers through direct mentorship and weekly interactions.
• Implement ideas quickly and communicate findings clearly to the broader AI safety community.
• Apply technical expertise in areas like pentesting, vulnerability research, or other offensive security approaches.

• In this fellowship, you'll conduct AI security research for four months, working to identify and address potential risks from advanced AI systems while producing publishable outputs.
• Develop empirical projects using external infrastructure like open-source models and public APIs.
• Collaborate with Anthropic researchers through direct mentorship and weekly interactions.
• Implement ideas quickly and communicate findings clearly to the broader AI safety community.
• Apply technical expertise in areas like pentesting, vulnerability research, or other offensive security approaches.

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.