Remote Adversarial AI Red Team Specialist

AuraOne, Inc.; United States; Remote; USD 34,000 - 55,000; Full time

Job summary

AuraOne, Inc. is seeking a remote Scheming Behavior Red Team Specialist to stress-test AI systems with adversarial prompts.

You will craft attack scenarios, document failures with rigorous reproduction steps, and pair each jailbreak with the violated rubric clause for patching gaps. Responsibilities include designing prompts, scoring defenses for single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a library of attack patterns while aligning with the red-team

Qualifications

• Experience red-teaming AI systems or adversarial ML work.
• Strong written communication in technical reports.
• Comfort working in policy-grey areas with clear documentation.
• 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 known weakness classes.
• 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 to safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new rubrics.
• Calibrate against broader red-team cohort to maintain coverage and severity.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Job description

AuraOne, Inc. is seeking a remote Scheming Behavior Red Team Specialist to stress-test AI systems with adversarial prompts.

You will craft attack scenarios, document failures with rigorous reproduction steps, and pair each jailbreak with the violated rubric clause for patching gaps. Responsibilities include designing prompts, scoring defenses for single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a library of attack patterns while aligning with the red-team