Remote AI Adversarial Red Teamer — Jailbreak & Prompt Testing

AI Trainer Jobs; United States; Remote; USD 96,000 - 138,000; Full time

Job summary

AuraOne is seeking a remote Malware Analysis Abuse Scenario Red Teamer to stress-test AI systems against adversarial prompts. You will design jailbreaks, document failure modes, and pair each exploit with the violated rubric clause to guide patching and regression testing.

As part of the role, you will evaluate defenses across single-turn and multi-turn interactions, triage new attack vectors, and report with rigorous reproduction steps to support model hardening before shipping to customers.

Qualifications

• Demonstrated experience red-teaming AI systems or adversarial ML work.
• Strong written communication; reports become the patch ticket.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Malware Analysis Abuse Scenario Red Teamer 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Malware analysis

Threat modeling

Adversarial testing

Security research

Job description

AuraOne is seeking a remote Malware Analysis Abuse Scenario Red Teamer to stress-test AI systems against adversarial prompts. You will design jailbreaks, document failure modes, and pair each exploit with the violated rubric clause to guide patching and regression testing.

As part of the role, you will evaluate defenses across single-turn and multi-turn interactions, triage new attack vectors, and report with rigorous reproduction steps to support model hardening before shipping to customers.