Offensive Security Engineer

The AI Security Institute is seeking an experienced offensive security engineer to build and break systems, focusing on finding and exploiting vulnerabilities across cloud, infrastructure, and application layers to evaluate frontier AI models. The role involves running engagements against evaluation infrastructure, building agent-assisted red-teaming harnesses, and collaborating with research teams to enhance cyber ranges and security protocols. This position offers the opportunity to publish research, present findings externally, and contribute to shaping AI development and government action.