Remote AI Safety Red-Team Evaluator: Adversarial Prompts

AuraOne, Inc.; United States; Remote; USD 96,000 - 165,000; Full time

Job summary

AuraOne, Inc. is seeking a remote contractor to help stress-test AI systems by designing adversarial prompts and documenting failures with rigorous repro steps. You will score defenses in single-turn and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns to improve red-team rubrics.

The role emphasizes thorough documentation in policy-grey areas and collaboration with the safety team to patch gaps.

Qualifications

• Experience red-teaming AI systems or adversarial ML work.
• Strong written communication; reports become the patch ticket.
• Comfort working in policy-grey areas with clear documentation of what was attempted and why.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts that probe known weakness classes for Scheming Behavior Risk Evaluator 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

Scheming Behavior Risk evaluation

AI safety

Red-team evaluation

Policy rubrics

Scheming

Behavior

Job description

AuraOne, Inc. is seeking a remote contractor to help stress-test AI systems by designing adversarial prompts and documenting failures with rigorous repro steps. You will score defenses in single-turn and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns to improve red-team rubrics.

The role emphasizes thorough documentation in policy-grey areas and collaboration with the safety team to patch gaps.