The AI Security Institute is seeking Research Engineers and Research Scientists for their Misuse Red Team, which focuses on developing and analyzing attacks and protections for large language models. Daily tasks may include designing and executing experiments, building automated attack tooling, and collaborating with frontier AI companies and government officials to inform policy and safeguard development. Candidates will have the opportunity to work on impactful research projects related to AI security and contribute to the understanding of advanced AI risks.
See how your résumé matches this role — and tailor it from what actually gets interviews.