Mountain View, California, US; New York City, New York, US
DeepMind seeks a Security Lead for the Agentic Red Team to lead a unit focused on adversarial AI. The role involves architecting attack scenarios, developing automated validation systems, and managing threat intelligence. Candidates need experience in offensive security, LLM architectures, and team leadership.
Red Teaming, Offensive Security, LLM architectures, agentic workflows, Python, Go, C++
benefits