AI Cyber Red Teamer

Attack frontier AI model safeguards to identify and document cyber vulnerabilities before deployment.
- Design novel attack strategies against AI guardrails; document failures and support model training improvements.
- Requires successful jailbreaks of frontier models and offensive security mindset with self-directed problem-solving.
- Highly valued: pentesting, red teaming, exploit development, or CTF competition experience.
- Python scripting, command-line proficiency, and agentic coding tool expertise preferred.

Attack frontier AI model safeguards to identify and document cyber vulnerabilities before deployment.
- Design novel attack strategies against AI guardrails; document failures and support model training improvements.
- Requires successful jailbreaks of frontier models and offensive security mindset with self-directed problem-solving.
- Highly valued: pentesting, red teaming, exploit development, or CTF competition experience.
- Python scripting, command-line proficiency, and agentic coding tool expertise preferred.

Trajectory Labs is a startup that builds RL environments for frontier AI labs to train robust, secure, and reliable models.