Intern

In this fellowship, you'll conduct empirical AI safety research with mentorship from industry experts. Collaborate on a research project aligned with Anthropic's safety priorities using external infrastructure. Receive direct mentorship from Anthropic researchers and connect with the broader AI safety community. Develop technical skills through hands-on work in areas like scalable oversight, adversarial robustness, or mechanistic interpretability. Produce public research outputs while receiving stipend, compute resources, and access to shared workspaces.

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.