Red Team - Cyber

The role

You will design and run evaluations of model cyber capabilities and safeguards. You will also test novel abuse risks in agentic systems and contribute to Safety Bug Bounty work.

What you will do

• Design and run rigorous evaluations of model cyber capabilities and safeguards.
• Conduct hands-on testing to understand what models can enable when used by experienced security practitioners.
• Distinguish benchmark or policy failures from behavior that creates meaningful real-world risk.
• Build and improve automated testing infrastructure.
• Test novel abuse risks in agentic systems.
• Translate findings into clear risk assessments and actionable recommendations.
• Contribute a portion of your time to Safety Bug Bounty work.

Required qualifications

• Substantial depth in cybersecurity, such as application security, penetration testing, vulnerability research, adversary simulation, or red-team operations, OR AI model evaluation, such as designing a
• Working literacy across both cybersecurity and model evaluation.
• The ability to write code and build practical testing tools.
• An attacker mindset.
• Clear written and verbal communication.
• Experience working across technical and non-technical teams.

Benefits

• Relocation assistance

Before you apply

• Background checks for applicants will be administered in accordance with applicable law.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.