Seeking a full-time Offensive Security Engineer, this remote position will manage the development of specialized agents to continuously identify and remediate vulnerabilities across OpenAI's infrastructure and applications, ensuring safe and reliable operations at scale. Key responsibilities Serve as the technical owner of offensive security agents, establishing architecture and evaluation strategies Design and build agents that test OpenAI's infrastructure and applications from various perspectives Develop complete vulnerability-management loops that validate impact, support remediation, and track progress Required qualifications Substantial hands-on offensive security experience with strong judgment on vulnerabilities and attack paths Extensive domain expertise in cloud security, Kubernetes, web application security, or Linux/macOS security Experience assessing complex environments beyond standardized scanners and checklists Proficiency in building production-quality software and agent systems with feedback loops Strong understanding of the differences between agent demonstrations and dependable production systems