Remote AI Adversarial Red Teamer – Jailbreak Scenarios

AuraOne; United States; On-site; USD 55,104 - 165,312; Part time

Benefits offered by this job

Contractor engagement

Remote work eligible (US)

Job summary

AuraOne is seeking a remote contractor for the Jailbreak Exploit Abuse Scenario Red Teamer role to stress-test AI systems against adversarial prompts. You will design jailbreak prompts, document failures with exact steps, and score defenses across single- and multi-turn conversations.

The ideal candidate has demonstrated red-teaming or adversarial ML experience, strong written reports, and the ability to operate in policy-grey areas with clear justification for actions taken.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication — reports become patch tickets.
• Comfort working in policy-grey areas with clear documentation of what was attempted and why.

Responsibilities

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

Jailbreak

Exploit

Security review

Adversarial testing

Threat modeling

Scenario evaluation

Job description

AuraOne is seeking a remote contractor for the Jailbreak Exploit Abuse Scenario Red Teamer role to stress-test AI systems against adversarial prompts. You will design jailbreak prompts, document failures with exact steps, and score defenses across single- and multi-turn conversations.

The ideal candidate has demonstrated red-teaming or adversarial ML experience, strong written reports, and the ability to operate in policy-grey areas with clear justification for actions taken.