Security Engineer, Agent Security

Position Overview

Join the Agent Security Team at OpenAI, where the mission is to accelerate the secure evolution of agentic AI systems. As a Security Engineer, you will design and implement robust security frameworks, develop comprehensive threat models, and partner across functions to safeguard critical assets. You will face complex security challenges and help shape long-term security strategies in a fast-paced, innovative environment. This role is based in Location: San Francisco, CA and operates under a hybrid work model.

Key Responsibilities

• Architect security controls for agentic AI – design, implement, and iterate on identity, network, and runtime-level defenses integrated with the Agent Infrastructure stack.
• Build production-grade security tooling – ship code that hardens safety monitoring pipelines across agent executions at scale.
• Collaborate cross-functionally – work daily with teams in Agent Infrastructure, product, research, safety, and security to balance security, performance, and usability.
• Influence strategy & standards – shape the long-term Agent Security roadmap, publish best practices, and help define industry standards for securing autonomous AI.

Required Qualifications

• Strong software-engineering skills in Python or at least one systems language (Go, Rust, C/C++), with a track record of shipping and operating secure, high-reliability services.
• Deep expertise in modern isolation techniques – experience with container security, kernel-level hardening, and related methods.
• Hands-on network security experience – implementing identity-based controls, policy enforcement, and secure large-scale telemetry pipelines.
• Clear, concise communication that bridges engineering, research, and leadership audiences; comfort influencing roadmaps and driving consensus.
• Bias for action & ownership – thrive in ambiguity, move quickly without sacrificing rigor, and elevate company-wide security standards from day one.
• Cloud security depth on at least one major provider (Azure, AWS, GCP), including identity federation, workload IAM, and infrastructure-as-code best practices.

Preferred Qualifications

• Familiarity with AI/ML security challenges – experience addressing risks associated with advanced AI systems (nice-to-have but valuable).

Benefits & Perks

• Schedule: Hybrid – 3 days in the office per week
• Benefits: Relocation assistance
• Compensation: $325K – $405K + Offers Equity