Lead Offensive Security Agent Engineer

OpenAI; Seattle (WA); On-site; USD 347,000 - 490,000; Full time

Job summary

OpenAI is seeking a Staff - Principal level offensive security domain expert to design and own a portfolio of production-grade agents that continuously identify, validate, and drive remediation of vulnerabilities across OpenAI's infrastructure and applications. You will combine deep security judgment with agent engineering to build systems that scale safely and autonomously.

You will collaborate with cross-functional teams to ensure findings are actionable, measurable, and aligned with safety

Qualifications

• Hands-on offensive security experience with strong judgment on which vulnerabilities to pursue.
• Domain expertise in cloud security, Kubernetes, web app security, and external attack-surface testing.
• Ability to decompose ambiguous problems into reliable systems and encode workflows into software.

Responsibilities

• Serve as technical owner of offensive security agents and define architecture, direction, and evaluation.
• Design and build agents that test OpenAI's infrastructure from multiple perspectives and integrate internal context.
• Build production-grade tooling with guardrails and human-in-the-loop controls for safety and reliability.
• Collaborate with security, infrastructure, product security, and engineering teams to ensure actionable findings.

Skills

Offensive security

Vulnerability research

Agent systems

Cloud security

Kubernetes security

Job description

OpenAI is seeking a Staff - Principal level offensive security domain expert to design and own a portfolio of production-grade agents that continuously identify, validate, and drive remediation of vulnerabilities across OpenAI's infrastructure and applications. You will combine deep security judgment with agent engineering to build systems that scale safely and autonomously.

You will collaborate with cross-functional teams to ensure findings are actionable, measurable, and aligned with safety