Offensive Security Engineer, Agent Products

Stack

Responsibilities

• ▹Conduct deep penetration tests of web applications, APIs, cloud services, identity/authorization flows, and CI/CD systems
• ▹Continuously hunt for exploitable vulnerabilities in the interactions between applications, infrastructure, tools, and models
• ▹Perform code review, architecture review, and hands-on exploitation to validate risk
• ▹Produce clear, actionable findings with reproduction steps, impact assessment, and remediation guidance
• ▹Partner with engineering teams to drive fixes and improve secure design patterns
• ▹Build tools, test harnesses, and automation to scale penetration testing
• ▹Share attacker-informed insights to improve threat models and defensive coverage

Requirements

• ▹7+ years of hands-on penetration testing or offensive security experience
• ▹Deep expertise finding, exploiting, and helping remediate vulnerabilities in complex production systems
• ▹Experience assessing modern technology products: web apps, APIs, cloud infrastructure, identity systems, and CI/CD pipelines
• ▹Experience designing or assessing the security of AI-powered systems
• ▹Experience with vulnerabilities specific to AI systems, including prompt injection, confused deputies, and unsafe tool use
• ▹Exceptional code review skills to identify novel and subtle vulnerabilities
• ▹Offensive security assessment experience in at least one hyperscaler cloud (Azure preferred)
• ▹Mastery across complex stacks: Kubernetes, containers, CI/CD pipelines, GitHub, macOS/Linux, Python backends, React frontends

Nice to have

• ▹Background or expertise in AI or data science
• ▹Experience in tech startups or fast-paced technology environments
• ▹Experience in related disciplines: software engineering, application security, detection engineering, SRE, IT infrastructure

Soft skills

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.