AI Abuse Red Teamer & Threat Simulator

OpenAI, Inc.; United States; Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Relocation assistance

Hybrid work model (3 days in office)

Job summary

OpenAI, Inc. seeks a Novel Abuse Red Teamer to advance adversarial testing and simulation protocols for AI models and products. You will design, execute, and refine testing methods using state-of-the-art tools in a hands-on red team approach.

The role is based in San Francisco with a hybrid work model (3 days in office) and relocation assistance for new hires. Strong background in application security and web testing is expected.

Qualifications

• Experience in application security, penetration testing, or red team operations.
• Hands-on testing of web applications and AI systems with attack simulations.
• Ability to translate complex findings into actionable insights.

Responsibilities

• Design and execute high-fidelity attack simulations that emulate sophisticated threat actor methodologies.
• Analyze testing outcomes and generate actionable insights to refine detection mechanisms.
• Serve as a technical bridge between security, product, and policy teams with an attacker mindset.
• Develop and integrate automation tools to streamline testing workflows and enable rapid iteration.
• Collaborate with internal stakeholders to align testing strategies with product and security goals.

Skills

application security

penetration testing

red team operations

web application security

abuse vector discovery

Tools

Burp Suite

Metasploit

Job description

OpenAI, Inc. seeks a Novel Abuse Red Teamer to advance adversarial testing and simulation protocols for AI models and products. You will design, execute, and refine testing methods using state-of-the-art tools in a hands-on red team approach.

The role is based in San Francisco with a hybrid work model (3 days in office) and relocation assistance for new hires. Strong background in application security and web testing is expected.