Red Team - Cyber

Skills

About the Role

You will design and run rigorous evaluations of model cyber capabilities and safeguards, conduct hands-on testing with security practitioners' techniques, build automated testing infrastructure, test abuse risks in agentic systems, and translate findings into actionable recommendations. You will also contribute to Safety Bug Bounty work.

Requirements

• Depth in cybersecurity or AI model evaluation
• Working literacy across both cybersecurity and model evaluation
• Ability to write code and build testing tools
• Attacker mindset
• Clear written and verbal communication
• Experience working across technical and non-technical teams

Responsibilities

• Design and run evaluations of model cyber capabilities and safeguards
• Conduct hands-on testing using harnesses, scaffolding and multi-step workflows
• Distinguish benchmark failures from real-world risk
• Build and improve automated testing infrastructure
• Test abuse risks in agentic systems such as prompt injection and agent hijacking
• Translate findings into risk assessments and recommendations
• Contribute to Safety Bug Bounty work

Benefits

• Equity
• Relocation assistance
• Medical, dental, and vision insurance with HSA employer contributions
• Health FSA, Dependent Care FSA, and commuter pre-tax accounts
• 401(k) with employer match
• Paid parental leave, medical and caregiver leave
• Flexible PTO
• 13+ paid company holidays and company office closures
• Mental health and wellness support
• Employer-paid life and disability coverage
• Learning and development stipend
• Daily meals in offices and meal delivery credits
• Charitable donation matching and wellness stipends