OpenAI
Security Engineer, Agent Security
$266K–$445K
San Francisco +1 · Full-time · Posted Jul 15, 2025
- Location
- San Francisco
US - Remote
About the job
Secures OpenAI’s agentic AI systems by building security controls, threat models, and scalable monitoring tools in partnership with infrastructure and other teams.
What you'll do
- Design, implement, and refine identity, network, and runtime defenses, including sandboxing and policy enforcement.
- Build production-grade tools to strengthen safety monitoring across agent executions at scale.
- Collaborate across teams and influence Agent Security strategy and standards.
What they ask for
- Strong software-engineering skills in Python or at least one systems language (Go, Rust, C/C++), with experience shipping and operating secure, high-reliability services.
- Expertise in modern isolation techniques, including container security and kernel-level hardening.
- Hands-on network security experience, including identity-based controls, policy enforcement, and secure large-scale telemetry pipelines.
- 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 and experience addressing risks associated with advanced AI systems.
Pay
$266K – $445K (USD, base salary)
Tools
Python, Go, Rust, C/C++, Azure, AWS, GCP
AI focus
Secures agentic AI systems and addresses risks associated with advanced AI systems.
Model-written summary · the original posting is authoritative