Jobs

The Anthropic Fellows Program, AI Security workstream, is a 4-month full-time research program designed to foster AI research and engineering talent, specifically in AI security. Fellows will receive funding, mentorship from Anthropic researchers, and access to resources to work on empirical projects aimed at producing public outputs like research papers. This program is ideal for individuals with a strong technical background, Python fluency, and a motivation to reduce catastrophic risks from advanced AI systems, with a particular interest in offensive security work or empirical ML research. Successful fellows may be considered for full-time roles at Anthropic, contributing to their mission of creating reliable, interpretable, and steerable AI systems.