AI Security Researcher: Insider Threat & Threat Modeling

Apollo Research in London and globally is seeking an AI Security Researcher to identify and remediate risks from AI agents, and to redefine insider-risk controls for the security of our workflows and products.

You will red-team internal surfaces, design novel threat mitigations, and translate findings into automated checks and CI/CD integrations. This hands-on role demands coding chops, sharp threat modelling, and clear written reporting.

#J-18808-Ljbffr