Principal Offensive Security Engineer: Autonomous Agents

Slope; United States; On-site; USD 220,000 - 300,000; Full time

Job summary

OpenAI is seeking a Staff - Principal level offensive security domain expert to build agents that continuously identify and coordinate remediation of vulnerabilities across OpenAI’s infrastructure and applications. You will be the technical owner of this effort, combining deep offensive security judgment with agent engineering to build a production system that can operate safely and reliably at scale.

As OpenAI increasingly uses automation, our security testing must become more automated,

Qualifications

• Substantial hands-on offensive security experience.
• Domain expertise in cloud security, Kubernetes and container security.
• Experience building production-quality software and agent systems.

Responsibilities

• Serve as the technical owner of OpenAI’s offensive security agents and define architecture and strategy.
• Design and build a portfolio of agents testing infrastructure and apps from multiple perspectives.
• Create guardrails, human-in-the-loop controls, and feedback loops for safe automation.
• Develop production-grade infrastructure for continuous operation, observability, and failure recovery.
• Collaborate with security, product, and engineering teams to ensure actionable findings.

Skills

Offensive security leadership

Cloud security

Kubernetes security

Production-grade software

Agent systems

Security testing automation

Guardrails and human-in-the-loop

Model safety evaluations

Security architecture

Job description

OpenAI is seeking a Staff - Principal level offensive security domain expert to build agents that continuously identify and coordinate remediation of vulnerabilities across OpenAI’s infrastructure and applications. You will be the technical owner of this effort, combining deep offensive security judgment with agent engineering to build a production system that can operate safely and reliably at scale.

As OpenAI increasingly uses automation, our security testing must become more automated,