CyberSecurity, Offensive Security Engineer

Safeguard agentic AI products by proactively identifying and exploiting vulnerabilities across agent interactions, cloud infrastructure, and foundational models. Lead red and purple team exercises and run penetration tests across AI-driven workflows and user-facing interfaces. Collaborate with defensive teams to convert offensive findings into detection engineering and incident response improvements, build and automate offensive tooling, and contribute to threat modeling and security architecture to keep agents resilient against evolving adversaries.