OpenAI

AI Research and Deployment

SecurityResearcher,AgenticAIThreats

$293–405k San Francisco, California, United States FULL TIME Remote Friendly
Market Sentiment
HIGH DEMAND

Neural analysis suggests this role is
optimal for Mid+ candidates.

The Brief

“Security Researcher, Agentic AI Threats at OpenAI. Skills: Security, AI threats, Software engineering, Infrastructure. Identify paths by which capable future internal AI agents could compromise OpenAI. Design security controls”

Industry & Context.

AI Research and Deployment

What They're Looking For.

Must Have

Deeply technical across security and modern infrastructure, Comfortable digging into the details of operating systems, cloud, containers, CI/CD, or distributed systems, Software engineering skills, Building prototypes yourself

Nice to Have

Experience securing cloud infrastructure, Deeply familiar with core components of the AI stack

What You'll Do.

Identify paths by which capable future internal AI agents could compromise OpenAI

Design security controls

Stress-test defenses with AI agent evaluations and penetration tests

How You'll Work.

Team & Collaboration

Engaging with stakeholders; Partnering with other staff

Full Job Description

ABOUT THE TEAM Preparedness is a critical Safety Research team at OpenAI, which is focused on mitigating AI threats to global security https://openai.com/index/updating-our-preparedness-framework/ that could scale to an extreme level of severity. Our work involves: 1. Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. 2. Mitigation. Keeping misuse safeguards, alignment tools, and security measures on track to adequately address extreme threats that might arise in the future. 3. Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework https://openai.com/index/updating-our-preparedness-framework/, and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society. ABOUT THE ROLE As AI agents become more capable at software engineering, and automate more of our internal work, they could become a dangerous cyber threat. People in this role will help OpenAI prepare for security threats from advanced AI agent insiders. IN THIS ROLE, YOU WILL: - Identify paths by which capable future internal AI agents could compromise OpenAI. - Design security controls - focusing on measures with long lead times that benefit from advanced preparation. - Stress-test defenses with AI agent evaluations and penetration tests YOU MIGHT THRIVE IN THIS ROLE IF YOU: - Are deeply technical across security and modern infrastructure, and are comfortable digging into the details of operating systems, cloud, containers, CI/CD, or distributed systems. - Have strong software engineering skills and enjoy building prototypes yourself. - Are interested in engaging with stakeholders and can do so effectively. - Bonus: have experience securing cloud infrastructure, and are deeply familiar with core components of the AI stack. Compensation Range: $293K - $405K USD About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that ge

Free ATS check

Applying for this Security Researcher, Agentic AI Threats role?

Most applicants get filtered before a human reads their resume. See if yours makes the cut.

How to Apply on Ashby

  • Ashby is a fast modern ATS — most applications take under 3 minutes.
  • The resume parser is strong; verify parsed experience dates and job titles.
  • Custom screening questions are often scored algorithmically — answer completely.
  • Location field affects geo-based screening; use your actual metro area.

ANONYMOUS · UNFILTERED

What do employees actually say about OpenAI?

Real rants from real employees. Read before you apply.

Read Company Rants →