Remote AI Safety Red-Team (Bilingual Russian STEM PhD)

AuraOne; United States; On-site; USD 66,000 - 72,000; Full time

Job summary

AuraOne is seeking a Bilingual Russian STEM Expert (PhD) for a remote AI Safety red-team track. You will craft adversarial prompts, document failures, and map each jailbreak to the violated rubric clause to help patch gaps before deployment.

You’ll review attacks, score defenses in single-turn and multi-turn conversations, and maintain a library of attack patterns while working asynchronously as a contractor from the US.

Qualifications

• Experience red-teaming AI systems or adversarial ML.
• Strong written communication; your reports become the patch ticket.
• Ability to document attempts and rationale in policy-grey areas.
• Familiarity with jailbreak, prompt-injection, and policy-bypass taxonomies.
• Available asynchronously for at least 10 hours per week.

Responsibilities

• Design adversarial prompts that probe known weakness classes for 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

Russian generalist evaluation

Job description

AuraOne is seeking a Bilingual Russian STEM Expert (PhD) for a remote AI Safety red-team track. You will craft adversarial prompts, document failures, and map each jailbreak to the violated rubric clause to help patch gaps before deployment.

You’ll review attacks, score defenses in single-turn and multi-turn conversations, and maintain a library of attack patterns while working asynchronously as a contractor from the US.