Remote Adversarial AI Red Teamer – Prompt Injection Focus

AuraOne, Inc.; United States; Remote; USD 83,000 - 138,000; Full time

Job summary

AuraOne, Inc. is seeking a Prompt Injection Abuse Scenario Red Teamer to remotely stress-test AI systems against adversarial prompts.

Reviewers craft attack scenarios, document failures, and tie each jailbreak to the violated rubric clause so the safety team can patch gaps. As a contractor, you will design adversarial prompts, document reproduction steps, score defenses across single-turn and multi-turn conversations, triage attack vectors, and maintain a library of patterns to keep coverage

Qualifications

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

Responsibilities

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

Prompt Injection Abuse Scenario Red Te

Security review

Adversarial testing

Threat modeling

Prompt

Injection

Job description

AuraOne, Inc. is seeking a Prompt Injection Abuse Scenario Red Teamer to remotely stress-test AI systems against adversarial prompts.

Reviewers craft attack scenarios, document failures, and tie each jailbreak to the violated rubric clause so the safety team can patch gaps. As a contractor, you will design adversarial prompts, document reproduction steps, score defenses across single-turn and multi-turn conversations, triage attack vectors, and maintain a library of patterns to keep coverage