Remote AI Adversarial Prompting Red Teamer

AuraOne, Inc.; United States; Remote; USD 124,000 - 165,000; Full time

Job summary

AuraOne, Inc. is seeking a Secure Code Abuse Scenario Red Teamer to design adversarial prompts, document failures, and map each jailbreak to the violated rubric clause. This remote contractor role supports adversarial evaluation to strengthen AI safety before shipping.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns to inform patches and improvements.

Qualifications

• Demonstrated experience red-teaming AI systems or adversarial ML work.
• Strong written communication; reports become patch tickets.
• Ability to document what was attempted and why in policy-grey areas.
• Familiarity with prompt-injection, jailbreak and policy-bypass taxonomies.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Design adversarial prompts to probe policy weaknesses.
• Document every successful attack with reproduction steps.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route to safety team with severity.
• Maintain a library of attack patterns and red-team rubrics.
• Calibrate against the broader red-team cohort for coverage.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Secure Code

Code

Security review

Adversarial testing

Threat modeling

Jailbreak awareness

Job description

AuraOne, Inc. is seeking a Secure Code Abuse Scenario Red Teamer to design adversarial prompts, document failures, and map each jailbreak to the violated rubric clause. This remote contractor role supports adversarial evaluation to strengthen AI safety before shipping.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns to inform patches and improvements.