Remote AI Safety Red-Team Expert — Spanish

AuraOne; United States; Remote; USD 59,000 - 65,000; Full time

Job summary

AuraOne is seeking a Bilingual Spanish Generalist Expert — AI Safety for a remote contractor role that tests AI systems against adversarial prompts and documents where failures occur. Reviewers craft attack scenarios, pair each successful jailbreak with the violated rubric clause, and help patch gaps in safety.

The role requires designing prompts, scoring defenses in both single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a personal library of patterns for

Qualifications

• Experience red-teaming AI systems or adversarial ML work.
• Strong written communication and documentation skills.
• Comfort with policy-grey areas and justification of attempts.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable async availability for 10+ hours per week.

Responsibilities

• Design adversarial prompts to probe known weakness classes for AI Safety assignments.
• Document every successful attack with reproduction steps and violated policy clause.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new rubrics.
• Calibrate against the broader red-team cohort to keep coverage and severity consistent.

Job description

AuraOne is seeking a Bilingual Spanish Generalist Expert — AI Safety for a remote contractor role that tests AI systems against adversarial prompts and documents where failures occur. Reviewers craft attack scenarios, pair each successful jailbreak with the violated rubric clause, and help patch gaps in safety.

The role requires designing prompts, scoring defenses in both single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a personal library of patterns for