Security Engineer, Agent Security

Details

The Agent Security Team's mission is to accelerate the secure evolution of agentic AI systems at OpenAI by designing, implementing, and continuously refining security policies, frameworks, and controls that defend critical assets, including user and customer data, against risks introduced by agentic AI.

As a Security Engineer, you will secure OpenAI's agentic AI systems by designing and implementing security frameworks, policies, and controls; developing threat models; partnering with the Agent Infrastructure group; and improving safety monitoring pipelines at scale. The role requires shipping solutions quickly while maintaining high standards for quality and security, influencing security strategy, and advancing the safe and responsible deployment of agentic AI systems.

Responsibilities

• Architect security controls for agentic AI, including identity, network, and runtime-level defenses such as sandboxing and policy enforcement, integrated with the Agent Infrastructure stack.
• Build and ship production-grade security tooling to harden safety monitoring pipelines across agent executions at scale.
• Collaborate with Agent Infrastructure, product, research, safety, and security teams to balance security, performance, and usability.
• Shape the long-term Agent Security roadmap.
• Publish best practices internally and externally.
• Help define industry standards for securing autonomous AI systems.

Requirements

• Strong software engineering skills in Python or at least one systems language, such as Go, Rust, C, or C++.
• Experience shipping and operating secure, high-reliability services.
• Deep expertise in modern isolation techniques, including container security, kernel-level hardening, and other isolation methods.
• Hands-on network security experience, including identity-based controls, policy enforcement, and secure large-scale telemetry pipelines.
• Clear and concise communication skills, with the ability to bridge engineering, research, and leadership audiences.
• Experience influencing roadmaps and driving consensus.
• Bias for action and ownership, with the ability to work effectively in ambiguity and move quickly without sacrificing rigor.
• Cloud security depth on at least one major provider, such as Azure, AWS, or GCP, including identity federation, workload IAM, and infrastructure-as-code best practices.
• Familiarity with AI/ML security challenges is valuable.

Benefits

• Base salary of $234,400–$385,000 per year, plus equity.
• Medical, dental, and vision insurance, with employer contributions to Health Savings Accounts.
• Pre-tax accounts for health, dependent care, and commuter expenses.
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off, paid company holidays, office closures, and sick or safe time.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Additional taxable fringe benefits may include charitable donation matching and wellness stipends.

OpenAI is an equal opportunity employer. Background checks and reasonable accommodations are handled in accordance with applicable law.