Remote AI Safety Red-Team Expert (Bilingual Arabic)

AuraOne; United States; On-site; USD 39,000 - 44,000; Part time

Job summary

AuraOne is seeking a Bilingual Arabic Generalist Expert — AI Safety to remotely stress-test AI systems through adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each jailbreak with the violated rubric clause to help patch gaps.

Responsibilities include designing prompts, documenting successful attacks with steps, scoring defenses, and triaging new vectors with severity. Independent contractor role with remote-US eligibility.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.

Responsibilities

• Design adversarial prompts that probe known weakness classes for Bilingual Arabic Generalist Expert — AI Safety 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

Arabic generalist

Job description

AuraOne is seeking a Bilingual Arabic Generalist Expert — AI Safety to remotely stress-test AI systems through adversarial prompts. Reviewers craft attack scenarios, document failures, and pair each jailbreak with the violated rubric clause to help patch gaps.

Responsibilities include designing prompts, documenting successful attacks with steps, scoring defenses, and triaging new vectors with severity. Independent contractor role with remote-US eligibility.