Remote AI Safety Red Team Specialist - Policy Compliance
Washington, District of Columbia, 20022, USA
Listed on 2026-10-04
-
IT/Tech
AI Evaluation, Data Annotation/ AI Labeling
AI Trainer Jobs is seeking a Policy Compliance Red Team Specialist to remotely stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and tie each jailbreak to the violated rubric clause for patching gaps.
Adversarial evaluation helps Aura One harden models before shipping to customers. Reviewers think like attackers, writing rigorous failure reports to enable reproduction, fixes, and regressions.
As a Remote AI Safety Red Team Specialist
- Policy Compliance, you will play an important part at AI Trainer Jobs in United States.
We appreciate your interest in this position.
Join AI Trainer Jobs and contribute to our ongoing work.
Take a moment to read everything above and see whether this role is right for you.
This posting is for the Remote AI Safety Red Team Specialist
- Policy Compliance role at AI Trainer Jobs, based in United States.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).