AI Security & Control Researcher — Threat Modeling for Watcher

Apollo Research seeks a security & control expert to shape threat models and improve Watcher, our coding agent security product. You will own threat modeling, failure modes, and monitor design in a startup-like, highly collaborative environment.

This IC role offers significant influence on product direction, potential leadership later, and collaboration with a team focused on AI safety, scheming detection, and control. London or San Francisco offices with flexible work options are available.

#J-18808-Ljbffr