AI Cyber Red Teamer

Trajectory Labs, PBC

Last seen in the source feed: Oct 13, 2026.

Application link last checked: Oct 10, 2026. The page matched this title; opening status remains unconfirmed.

Source listings can change. Check the employer's page for current availability and application requirements.

This role at a glance

Competition for attention. 314 open full-time AI Safety & Governance roles on Remote Impact right now, 23 of them posted in the last week.
Trajectory Labs, PBC has 5 other open remote roles here: see them all.

In this role, you'll attack the cyber safeguards of frontier AI models to find vulnerabilities and help train them out.
Design novel attack strategies against guardrails that prevent models from writing exploits.
Document security failures and identify robustness gaps against prompt injection and other attacks.
Test models' ability to assist with privilege escalation and real intrusions.
Shape system cards and deployment decisions through your security research findings.

Website

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

Draft a cover letter for this role or practise the questions you are likely to be asked.

Describe what you want and get your strongest matching jobs by email.