Advanced Adversarial Red Teamer for AI Security

OpenAI, Inc.; Seattle (WA); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Relocation assistance

Hybrid work model

Job summary

OpenAI is seeking a Novel Abuse Red Teamer to advance pre- and post-deployment testing, ensuring models and products resist evolving adversarial threats. You will design, execute, and refine innovative testing protocols using state-of-the-art tools with a hands-on red team approach.

This role requires strong web app security and application security experience, with collaboration across security, product, and policy teams.

Qualifications

• Experience with securing web applications and AI systems.
• Proven track record in adversarial or red team testing.
• Ability to translate findings into actionable security improvements.

Responsibilities

• Design and execute realistic attack simulations to uncover exploitation vectors.
• Analyze results and refine detection mechanisms and defenses.
• Bridge security, product, and policy teams to drive remediation.
• Develop automation tools to streamline testing workflows.
• Collaborate with stakeholders to align testing with product goals.

Skills

Application security

Penetration testing

Red team operations

Web application security

Adversarial testing

Strong communication

Tools

Burp Suite

Metasploit

Job description

OpenAI is seeking a Novel Abuse Red Teamer to advance pre- and post-deployment testing, ensuring models and products resist evolving adversarial threats. You will design, execute, and refine innovative testing protocols using state-of-the-art tools with a hands-on red team approach.

This role requires strong web app security and application security experience, with collaboration across security, product, and policy teams.