Job Overview
Location
San Francisco
Job Type
Full-time
Category
Security Engineer
Date Posted
May 19, 2026
Full Job Description
đź“‹ Description
- • Lead the development and maintenance of threat models focused on compromising OpenAI’s internal coding agents and automated security systems from insiders, Advanced Persistent Threats (APTs), or powerful AI agents.
- • Identify and prioritize critical security investments based on implementation lead-times, costs, and potential impact, ensuring proactive defense against extreme future AI-related threats.
- • Collaborate cross-functionally with Security, Infrastructure, Research, Legal, and Preparedness teams to align on technical implementation plans, tradeoffs, and risk mitigation strategies.
- • Directly execute technical initiatives when required, including prototyping security controls, writing and reviewing software, and coordinating engineering efforts across multiple teams.
- • Partner with internal and external penetration testers to identify, validate, and close gaps in the defenses surrounding autonomous AI agents and their supporting infrastructure.
- • Monitor and predict the evolving capabilities of frontier AI systems to anticipate how they might be weaponized or exploited to compromise internal systems.
- • Maintain and update OpenAI’s preparedness framework to ensure alignment with emerging threat vectors and mitigation targets for AI-driven security risks.
- • Design and implement workable security controls under tight constraints to address non-standard, high-stakes cybersecurity problems unique to autonomous AI agent environments.
- • Serve as the technical lead for preparedness initiatives that protect critical internal systems from compromise that could cascade across the company’s infrastructure.
- • Translate complex technical risks into actionable strategic priorities for leadership, ensuring resources are allocated to the most urgent and high-impact security needs.
- • Engage with advanced cyberoffensive actors’ tactics, techniques, and procedures to inform defense strategies against similarly capable adversaries targeting AI systems.
- • Ensure alignment between AI safety research, operational security, and threat mitigation pathways, bridging gaps between theoretical risks and practical implementation.
- • Contribute to the broader mission of securing OpenAI’s AI agents as the company increasingly relies on autonomous coding systems for research and deployment.
- • Maintain strict confidentiality and integrity of proprietary, sensitive, and non-public information accessed through secure systems and threat intelligence channels.
🎯 Requirements
- • Proven experience working directly with advanced persistent threat (APT) actors or other capable cyberoffensive groups
- • Exceptional hands-on technical execution ability in cybersecurity, including prototyping controls, writing/reviewing code, and leading technical implementations
- • Demonstrated leadership in managing technical programs or teams focused on cybersecurity or AI system safety
- • Deep understanding of threat modeling methodologies for complex, autonomous software systems
- • Experience identifying and prioritizing security investments based on implementation timelines, costs, and potential impact
- • Ability to creatively reason about non-standard security problems and design practical controls under tight constraints
🏖️ Benefits
- • Opportunity to work on high-impact, mission-critical AI safety and security challenges at the forefront of global technology
- • Collaboration with world-leading researchers and engineers in AI safety, infrastructure, and cybersecurity
- • Access to cutting-edge AI systems and tools used in real-world research and deployment
- • Supportive, mission-driven culture focused on responsible AI development and global societal benefit
Skills & Technologies
Senior
Onsite
About OpenAI, Inc.
OpenAI is a San Francisco-based artificial intelligence research and deployment company founded in 2015. It develops large-scale AI models such as GPT, DALL-E, and Codex, providing cloud APIs and consumer applications like ChatGPT. Originally established as a non-profit, it later created a capped-profit subsidiary to attract capital while maintaining its mission to ensure artificial general intelligence benefits all of humanity.
Get more remote jobs like this
Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.
Newsletter
Weekly remote jobs and featured talent.
No spam. Only curated remote roles and product updates. You can unsubscribe anytime.
