Adversarial AI Safety Red Team Evaluator

AI Trainer Jobs; United States; Remote; USD 90,000 - 96,000; Full time

Job summary

AuraOne is seeking a Manipulation Risk Risk Evaluator for a remote, contractor role focused on stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each jailbreak with the violated rubric clause so the safety team can patch gaps.

Adversarial evaluation helps harden models before they ship to customers. Applicants should push on refusal boundaries, document rigorously, and score defenses across single-turn and multi-turn

Qualifications

• Experience red-teaming AI systems or adversarial ML work.
• Ability to document attacks with reproduction steps and patch tickets.
• Strong written communication and ability to document policy-rationale clearly.

Responsibilities

• Design adversarial prompts that probe weakness classes (jailbreak, policy bypass, prompt injection).
• Document every successful attack with reproduction steps and the policy clause it violated.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to the safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new red-team rubrics.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Manipulation Risk Risk evaluation

AI safety

Red-team evaluation

Policy rubrics

Manipulation

Risk

Job description

AuraOne is seeking a Manipulation Risk Risk Evaluator for a remote, contractor role focused on stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each jailbreak with the violated rubric clause so the safety team can patch gaps.

Adversarial evaluation helps harden models before they ship to customers. Applicants should push on refusal boundaries, document rigorously, and score defenses across single-turn and multi-turn