Novel Abuse Red Teamer

OpenAI•San Francisco, CA

1d•$158,400 - $320,000•Hybrid

About The Position

The Intelligence and Investigations team works to support the safe, responsible deployment of AI by detecting and mitigating abuse. It uses testing methodologies to identify vulnerabilities and emerging threats, partnering with product, policy, and engineering teams on defenses against evolving adversarial challenges. The Novel Abuse Red Teamer advances pre- and post-deployment testing at OpenAI to help keep models and products resilient against real-world adversarial threats. The role designs, executes, and refines adversarial testing and simulation protocols, uses a hands-on red-team approach to simulate threat actor methodologies, and conducts application testing to uncover novel abuse vectors. It connects security, product, and policy teams, translating adversarial testing findings into insights that strengthen detection mechanisms and product defenses. The position is based in San Francisco, California, with a hybrid work model requiring three days in the office per week. Relocation assistance is offered to new employees.

Requirements

Experience in application security, penetration testing, or red team operations, including a track record of adversarial testing and simulation.
Strong technical background in web application security and hands-on experience testing web applications, AI systems, and unique attack surfaces.
An attacker mindset and interest in identifying novel abuse vectors in live environments.
Ability to translate complex technical findings into actionable insights.
Demonstrated ability to work cross-functionally in fast-paced, dynamic environments, manage complex product ecosystems, and drive rapid security enhancements.
Commitment to continuous learning and innovative security methodologies.

Responsibilities

Design and execute realistic attack simulations that emulate sophisticated threat actor methodologies and uncover exploitation vectors through red teaming and application testing.
Analyze testing outcomes and generate actionable insights to refine detection mechanisms and improve the overall security posture.
Bridge security, product, and policy teams so that adversarial testing insights inform defense strategies and remediation efforts.
Develop and integrate automation tools to streamline testing workflows and support rapid iteration in response to emerging threats.
Collaborate with internal stakeholders to align testing strategies with evolving product needs and security objectives.