Research Engineer and Research Scientist - Alignment Red Team

The AI Security Institute is seeking Research Engineers and Research Scientists to join its Alignment Red Team, focusing on detecting and evaluating misalignment in frontier AI systems. The role involves conducting novel research to develop techniques for finding misalignment, performing pre- and post-deployment evaluations, and sharing findings with governments and AI companies to inform policy and safety measures. This position offers the opportunity to work with leading experts, access to frontier models, and direct influence on global AI governance.