Remote AI Safety Red‑Team Strategist

AuraOne; United States; A distancia; USD 83.000 - 96.000; A tiempo parcial

Descripción de la vacante

AI Trainer Jobs seeks an AI Safety Practitioner for remote engagement as a contractor. You will craft adversarial prompts to test AI systems, document failures with rigorous reproduction steps, and map each jailbreak to the violated policy clause for patching gaps.

Responsibilities include scoring defenses across turns, triaging new attack vectors with severity, and maintaining libraries of attack patterns to evolve red-team rubrics.

Formación

• Experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication: reports become patch tickets.
• Comfort documenting reasoning in policy-grey areas with clear justification.

Responsabilidades

• Design adversarial prompts that probe known weakness classes.
• Document every successful attack with reproduction steps and policy clause violated.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route to safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new rubrics.

Conocimientos

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

AI Safety Practitioner evaluation

Descripción del empleo

AI Trainer Jobs seeks an AI Safety Practitioner for remote engagement as a contractor. You will craft adversarial prompts to test AI systems, document failures with rigorous reproduction steps, and map each jailbreak to the violated policy clause for patching gaps.

Responsibilities include scoring defenses across turns, triaging new attack vectors with severity, and maintaining libraries of attack patterns to evolve red-team rubrics.