Similar Jobs

See all

The AI Security Fellow at Anthropic offers several exciting opportunities:

  • Fellows will undergo a project selection & mentor matching process.
  • There is direct mentorship from Anthropic researchers.
  • Fellows gaining access to a shared workspace.

Fellows contribute to cutting-edge AI security research:

  • Fellows work on an empirical project aligned with Anthropic's research priorities.
  • Projects may involve finding exploits or strengthening red teams.
  • There is a goal of producing a public output, such as a paper submission.

Fellows accelerate their careers in AI safety:

  • There is connection to the broader AI safety research community.
  • Fellows receive funding for compute and research expenses.
  • Strong performance may lead to a full-time offer at Anthropic.

Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems, striving for AI to be safe and beneficial for users and society.

Apply for This Position