Offensive Security Engineer (AI)

TL;DR

Offensive Security Engineer (AI): Conducting deep penetration testing of agent-powered products and model-integrated surfaces with an accent on identifying realistic vulnerabilities in complex AI-driven ecosystems. Focus on hunting for exploitable vulnerabilities in interactions between applications, infrastructure, and AI models to drive durable security fixes.

Location: Remote - US (New York City, Seattle, Washington, DC, and San Francisco)

Salary: $347K – $490K + Equity

Company

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

What you will do

• Conduct deep penetration tests of agent-powered products, including web applications, APIs, cloud services, and model-integrated surfaces.
• Hunt for exploitable vulnerabilities in the interactions between applications, infrastructure, tools, and AI models.
• Perform code and architecture reviews to identify subtle or novel failure modes.
• Produce actionable findings with reproduction steps, impact assessment, and remediation guidance.
• Build tools, test harnesses, and automation to scale penetration testing across evolving product surfaces.
• Partner with engineering teams to drive fixes and improve secure design patterns.

Requirements

• 7+ years of hands-on experience in penetration testing, product security, or offensive security.
• Deep expertise in exploiting and remediating vulnerabilities in complex production systems.
• Experience assessing AI-powered systems, including prompt injection, confused deputies, and unsafe tool use.
• Mastery of complex stacks: Kubernetes, container environments, CI/CD pipelines, and GitHub security.
• Proficiency in Python-based web services and React-based frontend applications.
• Must be based in the United States.

Nice to have

• Background or expertise in AI or data science.
• Prior experience in fast-paced tech startups.
• Experience in Software Engineering, SRE, or Detection Engineering.

Culture & Benefits

• Commitment to a robust security culture that prioritizes impact and enables researchers.
• Opportunity to work with cutting-edge agentic products like Codex and Operator.
• Collaborative environment focused on preparing for future transformative technologies.
• Competitive compensation package including equity.