AI Red Teamer

Trajectory Labs is a stealth AI security startup working with leading AI companies. We're hiring to red-team products from frontier AI labs. Your work will contribute to making AI systems safer by helping identify and mitigate failure modes before deployment. Your work will contribute to making AI systems safer by helping identify and mitigate failure modes before deployment. What you'll gain: Hands-on experience with frontier AI security, High-impact work on cutting-edge AI safety challenges, High ownership and autonomy, Strong references for future roles in AI safety.

This role creates positive change by identifying and mitigating security vulnerabilities in frontier AI systems before deployment, helping prevent potential harms from advanced AI technologies.

Successful jailbreaks of frontier models (GPT-5, Claude, Gemini, etc.), Self-directed - you work independently with minimal guidance, Participation in jailbreaking competitions, Comfortable scripting in Python, command line and git basics, Power user of agentic coding tools (e.g. spec-driven development, multi-agent orchestration), Professional experience in security consulting or ML security, Prior work with AI labs or safety organizations

No benefits information provided in the job description.

Trajectory Labs appears to be an organization focused on AI safety and security, working with frontier AI labs to test and secure advanced AI systems.