Red Team Engineer, Safeguards

Highlights

• Adversarially test product surfaces to uncover vulnerabilities before attackers do.
• Design full kill-chain attacks emulating real-world threat actors' objectives.
• Research novel testing approaches for emerging agent systems and tool use.

What they offer

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space for collaboration

Ideal candidate

Creative security-minded thinker who loves thinking like an attacker to protect AI systems. You combine curiosity about emerging AI risks with clear communication and collaboration across teams.

Requirements

• Experience in penetration testing, red teaming, or application security
• Experience in model jailbreaking and testing large-scale agentic workflows for prompt injection
• Strong technical skills in web application security including security testing tools
• Experience building custom automation including LLM-specific testing frameworks
• Track record of discovering novel attack vectors and chaining vulnerabilities
• Public body of work such as CVEs, blog posts, or disclosed bug bounty reports
• Strong written and verbal communication skills
• Bachelor's degree or equivalent combination of education, training, and experience