Teams at AI Security Institute

The Red Team conducts research to identify vulnerabilities in AI systems, collaborating with AI companies and governments to inform policy and improve safety measures.

The role involves designing and running studies on human-AI interaction, focusing on the societal impacts of AI. Candidates will conduct RCTs and collaborate with research scientists, requiring skills in statistical modeling and coding.

Design and build reliable systems, manage technical projects, write high-quality Python code, and collaborate with researchers to deliver functional software solutions.