AI Security Institute seeks exceptional cybersecurity experts to work on frontier AI security. You’ll design cyber ranges, run pre-deployment tests, and validate model behaviours, collaborating with engineers and researchers who prioritise impact and autonomy in a mission-driven setting.
Role offers exposure to world-class evaluations, mentoring, and the chance to influence safety standards for frontier AI. Hybrid work from London with global partnerships and strong government ties.
#J-18808-Ljbffr…
