Novel Abuse Red Teamer
OpenAISan Francisco, Seattle, US - RemoteRemote
Needs a free Superjobs account. You'll finish on OpenAI's Ashby page.
Skill score
Summary
The Novel Abuse Red Teamer designs and runs adversarial attack simulations against OpenAI models and products to uncover new abuse vectors before and after deployment, then turns findings into detection and defense improvements. It suits a hands-on security tester with an attacker mindset and a background in application security or penetration testing who can also communicate with product and policy teams.
- Estimated salary
- Est. $102k–153k/yr
- Estimated for a mid-level role, ~3 yrs experience (typical for the level), United States. Not published by the employer.
- Work mode and location
- Remote, San Francisco, Seattle, US - Remote
- Employment type
- Full-time
Job description
Overview
About the Team
The Intelligence and Investigations team is dedicated to ensuring the safe, responsible deployment of AI by rapidly detecting and mitigating abuse. Our team leverages cutting-edge testing methodologies to uncover vulnerabilities and emerging threats, helping safeguard OpenAI’s products and users. We work closely with cross-functional partners across product, policy, and engineering to drive a comprehensive defense strategy against evolving adversarial challenges.
As a Novel Abuse Red Teamer, you’ll advance our pre- and post-deployment testing efforts at OpenAI, ensuring our models and products remain resilient against evolving, real-world adversarial threats.
We are seeking a self-starter to design, execute, and refine innovative adversarial testing and simulation protocols that leverage state-of-the-art tools and a hands-on red team approach. In this role, you will simulate threat actor methodologies and conduct rigorous application testing to uncover novel abuse vectors.
You will serve as a critical technical bridge between our security, product, and policy teams by employing an attacker mindset and advanced red team tactics to drive actionable insights that strengthen our detection mechanisms and overall product defenses. The ideal candidate will have a strong background in application security or penetration testing, with hands-on experience in web application security and proficiency in tools such as Burp Suite, Metasploit, and similar.
Roles and responsibilities
- Design and execute high-fidelity, realistic attack simulations that emulate sophisticated threat actor methodologies, uncovering hidden exploitation vectors through advanced red teaming and application testing techniques.
- Analyze testing outcomes and generate actionable insights to refine our detection mechanisms, ultimately bolstering our overall security posture.
- Serve as a crucial technical bridge between our security, product, and policy teams, ensuring that insights from adversarial testing inform broader defense strategies and remediation efforts.
- Develop and integrate automation tools to streamline testing workflows and enable rapid iteration in response to emerging threats.
- Collaborate closely with internal stakeholders to align testing strategies with evolving product needs and security objectives.
Skills required
Top skills
- Application security
- Penetration testing
- Red team operations
- Web application security
All skills (4)
- Adversarial testing
- Burp Suite
- Metasploit
- Automation tools
Qualifications
We value professionals with excellent communication skills, a commitment to continuous learning, and a passion for securing AI technologies through innovative testing methodologies.
- Experience in application security, penetration testing, or red team operations, with a proven track record of executing adversarial testing and simulation protocols.
- A strong technical background in web application security, coupled with hands-on expertise performing security testing of web applications, AI systems, and highly unique attack surfaces.
- An attacker mindset and a passion for identifying novel abuse vectors in live environments, along with the ability to translate complex technical findings into actionable insights.
- Demonstrated success in working cross-functionally within fast-paced, dynamic environments, managing complex product ecosystems, and driving rapid security enhancements.
- Committed to continuous learning, innovation, and the pursuit of cutting-edge security methodologies to protect and advance AI technologies.
Other details
This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.
Company info
About OpenAI
OpenAI is an AI research and deployment company that builds AI systems and deploys them to the world through its products. Its customers and businesses use these AI products across their operations, with support from its sales, solutions, and support teams.