Security Engineer, Agent Security

The role

You will design and implement security frameworks, policies, and controls to protect agentic AI systems. You will architect security controls, build production-grade tooling, and collaborate with infrastructure and research teams.

What you will do

• Architect security controls for agentic AI including identity, network, and runtime-level defenses.
• Build production-grade security tooling to harden safety monitoring pipelines.
• Collaborate cross-functionally with Agent Infrastructure, product, research, safety, and security teams.
• Influence strategy and standards by shaping the Agent Security roadmap and publishing best practices.

Required qualifications

• Strong software-engineering skills in Python or at least one systems language (Go, Rust, C/C++).
• Track record of shipping and operating secure, high-reliability services.
• Deep expertise in modern isolation techniques such as container security and kernel-level hardening.
• Hands-on network security experience implementing identity-based controls, policy enforcement, and secure large-scale telemetry pipelines.
• Clear, concise communication to bridge engineering, research, and leadership audiences.
• Cloud security depth on at least one major provider (Azure, AWS, GCP) including identity federation, workload IAM, and infrastructure-as-code best practices.

Nice to have

• Familiarity with AI/ML security challenges

About the company

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