Red Team Specialist - Cyber

Details

The Intelligence and Investigations team helps ensure the safe, responsible deployment of AI by detecting and mitigating abuse. This role focuses on evaluating cyber capabilities in AI models and determining whether safeguards remain effective against increasingly sophisticated attacks. The position combines scaled evaluation with expert-driven cybersecurity testing and includes testing abuse risks in agentic systems.

The role is based in San Francisco, California, or Seattle, Washington, with a hybrid work model requiring three days in the office per week.

Responsibilities

• Design and run rigorous evaluations of model cyber capabilities and safeguards, including policy adherence, correct refusal, over-refusal, resilience to jailbreaking, and other adversarial techniques.
• Conduct hands-on testing to understand what models can enable for experienced security practitioners using task-specific harnesses, scaffolding, and multi-step workflows.
• Distinguish benchmark or policy failures from behavior that creates meaningful real-world risk by considering feasibility, attacker uplift, reliability, and capabilities already available elsewhere.
• Build and improve automated testing infrastructure for repeatable measurement, rapid iteration, and statistically grounded analysis across models and product surfaces.
• Test abuse risks in agentic systems, including indirect prompt injection, agent hijacking, and other adversarial manipulation of systems that use tools or external information.
• Translate findings into risk assessments and actionable recommendations for Security, Research, Product, Policy, and Engineering teams.
• Contribute to Safety Bug Bounty work, particularly reports requiring cybersecurity expertise.

Requirements

• Substantial experience in at least one of the following areas:
  • Cybersecurity, including application security, penetration testing, vulnerability research, adversary simulation, or red-team operations.
  • AI model evaluation, including designing and running evaluations, building agentic harnesses, automating adversarial testing, constructing datasets, or analyzing model behavior at scale.
• Working knowledge of both cybersecurity and model evaluation, with interest in developing additional depth outside the primary area.
• Ability to write code and build practical testing tools for automating experiments, orchestrating models, or analyzing results.
• An attacker mindset and interest in discovering failure modes that standard evaluations may not capture.
• Clear written and verbal communication skills, including the ability to explain technical findings, limitations, and risks to audiences with different backgrounds.
• Experience working across technical and non-technical teams to move from findings to decisions, mitigations, or follow-up tests.

Benefits

• Equity, performance-related bonuses for eligible employees, and comprehensive benefits.
• Medical, dental, and vision insurance, with employer contributions to Health Savings Accounts.
• Pre-tax flexible spending and commuter accounts.
• 401(k) retirement plan with employer match.
• Paid parental, medical, caregiver, and sick or safe leave.
• Paid time off and company holidays.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Additional benefits may include charitable donation matching and wellness stipends.