Remote AI Adversarial QA Specialist

AuraOne; United States; On-site; USD 82,656 - 165,312; Full time

Job summary

AuraOne is seeking an AI Policy Compliance Document QA Specialist for a remote, contractor role focused on stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and map each jailbreak to the violated policy clause to enable patching.

Responsibilities include designing adversarial prompts, documenting attacks with reproducible steps, scoring defenses across turns, triaging new vectors, and maintaining attack pattern libraries.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for AI Policy Compliance Document QA Specialist work.
• Strong written communication — your reports become the patch ticket.
• Comfort working in policy-grey areas with clear documentation of what was attempted and why.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for AI Policy Compliance Document QA Specialist 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.
• Calibrate against the broader red-team cohort to keep coverage and severity consistent.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Document annotation

Legal reasoning

Policy review

Risk analysis

Policy

Compliance

Job description

AuraOne is seeking an AI Policy Compliance Document QA Specialist for a remote, contractor role focused on stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and map each jailbreak to the violated policy clause to enable patching.

Responsibilities include designing adversarial prompts, documenting attacks with reproducible steps, scoring defenses across turns, triaging new vectors, and maintaining attack pattern libraries.