Job Overview
Location
San Francisco
Job Type
Full-time
Category
Security Engineer
Date Posted
May 19, 2026
Full Job Description
đź“‹ Description
- • Identify potential pathways by which future internal AI agents could compromise OpenAI’s systems, data, or operations, with a focus on agentic AI behaviors that mimic insider threats.
- • Design and propose proactive security controls that have long lead times, ensuring mitigation strategies are in place before advanced AI agents become capable of exploiting vulnerabilities.
- • Conduct stress-tests on OpenAI’s security infrastructure using AI agent evaluations and simulated penetration tests to uncover weaknesses in current defenses.
- • Collaborate with engineering, safety, and infrastructure teams to integrate security measures into the development lifecycle of AI systems and internal tooling.
- • Monitor and analyze the evolving capabilities of frontier AI models to predict how their increasing autonomy and software engineering proficiency may enable new attack vectors.
- • Develop prototypes and experimental systems to model AI-driven security breaches, enabling real-world testing of defensive architectures before deployment.
- • Maintain alignment with OpenAI’s Preparedness Framework to ensure security targets are scientifically grounded, measurable, and responsive to emerging threats.
- • Work closely with internal stakeholders to translate high-level threat scenarios into actionable technical requirements for security teams and product developers.
- • Document threat models, attack surfaces, and mitigation strategies with precision to support internal audits, regulatory preparedness, and cross-team knowledge sharing.
- • Stay abreast of advancements in cloud infrastructure, containerization, CI/CD pipelines, distributed systems, and AI stack components to anticipate novel exploitation techniques.
- • Engage with technical and non-technical teams to communicate complex security risks and the importance of long-term preparation in high-stakes AI development.
- • Independently lead security research initiatives with minimal oversight, prioritizing efforts that address the most severe and plausible future threats.
- • Contribute to the broader safety research community by publishing findings, participating in internal reviews, and advising on policy decisions related to AI agent security.
- • Operate in a fast-paced environment where threats evolve rapidly, requiring agility, critical thinking, and sustained focus on high-impact, low-probability scenarios.
- • Apply deep technical expertise in operating systems, network security, access control systems, and runtime environments to assess how AI agents might bypass traditional detection mechanisms.
- • Evaluate the security implications of autonomous AI agents interacting with internal APIs, code repositories, deployment pipelines, and privileged environments.
- • Balance theoretical threat modeling with practical implementation, ensuring proposed controls are feasible, scalable, and compatible with OpenAI’s existing technical stack.
- • Remain vigilant to emerging trends in adversarial AI, autonomous agent systems, and machine learning model manipulation to anticipate next-generation insider threats.
🎯 Requirements
- • Deep technical expertise in security and modern infrastructure, including operating systems, cloud platforms, containers, CI/CD, and distributed systems
- • Strong software engineering skills with the ability to build and iterate on security prototypes independently
- • Experience securing cloud infrastructure and deep familiarity with core components of the AI stack
- • Ability to effectively engage with cross-functional stakeholders and communicate complex technical risks
- • Proven track record of conducting penetration tests, vulnerability assessments, or AI agent evaluations in high-stakes environments
- • Interest in and understanding of frontier AI capabilities and their potential for misuse as autonomous agents
🏖️ Benefits
- • Compensation range of $293K - $405K USD
- • Opportunity to work on mission-critical safety research with direct impact on global AI security
- • Collaborative environment with leading experts in AI safety, engineering, and policy
- • Access to cutting-edge AI models and infrastructure for research and testing
Skills & Technologies
Onsite
$293k-405k
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.
