Offensive Security Engineer, Agent Security

We are seeking an exceptional Principal-level Offensive Security Engineer to challenge and strengthen OpenAI s security posture. This role is an opportunity to engage broadly and deeply, craft innovative attack simulations, collaborate closely with defensive teams, and influence strategic security improvements across the organization.

This role will be primarily focused on continuously testing our agent powered products like codex and operator. These systems are uniquely valuable targets because they are rapidly evolving, have access to perform sensitive actions on behalf of users, and have large, diverse attack surfaces.

You will play a crucial role in securing our agents by hunting for realistic vulnerabilities that emerge from the interactions between the applications, infrastructure, and models that power them.

• 7+ years of hands-on red team experience or exceptional accomplishments
• Deep expertise conducting offensive security operations within modern technology companies
• Experience designing, developing, or assessing the security of AI-powered systems
• Experience finding, exploiting and mitigating AI vulnerabilities like prompt injection
• Exceptional skill in code review, identifying novel and subtle vulnerabilities
• Proven experience performing offensive security assessments in hyperscaler cloud environments