Remote Adversarial AI Safety Evaluator

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

Job summary

AuraOne is seeking a Chemicals Safety Risk Evaluator in a remote, US-eligible red-team track to stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and tie each successful jailbreak to the violated policy clause so the safety team can patch gaps.

As an independent contractor, you will design prompts, score defenses, triage new attack vectors, and maintain a personal library of attack patterns.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML for safety risk roles.
• Strong written communication; reports become patch tickets.
• Familiarity with prompt-injection, jailbreak, policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts to probe known weakness classes (jailbreak, policy bypass, prompt injection) for Chemical Safety Risk Evaluator assignments.
• 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

Documentation

Written communication

Async work

Multilingual ability

Job description

AuraOne is seeking a Chemicals Safety Risk Evaluator in a remote, US-eligible red-team track to stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures, and tie each successful jailbreak to the violated policy clause so the safety team can patch gaps.

As an independent contractor, you will design prompts, score defenses, triage new attack vectors, and maintain a personal library of attack patterns.