Remote AI Adversarial Testing Red Team Engineer

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

Job summary

AuraOne is seeking a Threat Intelligence Abuse Scenario Red Teamer to stress-test AI systems with adversarial prompts in a remote contractor role. Reviewers craft attack scenarios, document failure modes, and tie each jailbreak to the violated rubric clause for patching.

You'll evaluate defenses across single-turn and multi-turn interactions, score robustness, and triage emerging vectors for the safety team to address, with hourly compensation after interview.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Excellent written documentation of attacks and patches.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection).
• Document every successful attack with reproduction steps and policy clause 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

Threat intelligence

Security review

Adversarial testing

Threat modeling

Intelligence

Job description

AuraOne is seeking a Threat Intelligence Abuse Scenario Red Teamer to stress-test AI systems with adversarial prompts in a remote contractor role. Reviewers craft attack scenarios, document failure modes, and tie each jailbreak to the violated rubric clause for patching.

You'll evaluate defenses across single-turn and multi-turn interactions, score robustness, and triage emerging vectors for the safety team to address, with hourly compensation after interview.