Description

You will participate in a 4-month full-time research fellowship focused on AI security, working on an empirical project with mentorship from Anthropic researchers and access to external compute resources. The goal is to produce a public output such as a paper submission.

Requirements

• Strong technical background in computer science, mathematics, or physics
• Motivated by AI safety and beneficial outcomes
• Able to implement ideas quickly and communicate clearly
• Thrive in fast-paced, collaborative environments

Responsibilities

• Conduct 4 months of full-time empirical AI security research
• Work on a project aligned with Anthropic's research priorities
• Produce a public output (e.g., paper submission)
• Collaborate with Anthropic researchers and the broader AI safety community