Remote AI Safety Red-Team Specialist — Portuguese

AuraOne; United States; A distancia; USD 55.000 - 61.000; Jornada completa

Descripción de la vacante

AI Trainer Jobs is seeking a Bilingual Portuguese Generalist Expert — AI Safety for a remote red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and tie each jailbreak to the rubric clause it violated so the safety team can patch gaps.

As a contractor, you will design adversarial prompts, document steps with policy clauses, and score defenses across conversations.

Formación

• Experience red-teaming AI systems or adversarial ML.
• Multilingual cross-language attack testing experience.
• Proven ability to document attacks and patch tickets.
• Strong written communication skills.

Responsabilidades

• Design adversarial prompts probing known weakness classes (jailbreak, policy bypass, prompt injection) for 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.

Conocimientos

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Multilingual testing

Strong written communication

Descripción del empleo

AI Trainer Jobs is seeking a Bilingual Portuguese Generalist Expert — AI Safety for a remote red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and tie each jailbreak to the rubric clause it violated so the safety team can patch gaps.

As a contractor, you will design adversarial prompts, document steps with policy clauses, and score defenses across conversations.