Remote Dual-Use AI Red Team Specialist

AuraOne; United States; On-site; USD 82,656 - 179,088; Full time

Job summary

AuraOne is hiring for a remote Dual-Use Research Red Team Specialist, a contractor role to stress-test AI systems against adversarial prompts. You will craft attack scenarios, document failures with rigorous reproduction steps, and map each jailbreak to the violated policy clause for patching by the safety team.

You will score defenses across single-turn and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns with evolving rubrics.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML.
• Strong written communication — reports become the patch ticket.
• Comfort working in 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

Dual Use Research Red Team evaluation

AI safety

Red-team evaluation

Policy rubrics

Multilingual testing

Job description

AuraOne is hiring for a remote Dual-Use Research Red Team Specialist, a contractor role to stress-test AI systems against adversarial prompts. You will craft attack scenarios, document failures with rigorous reproduction steps, and map each jailbreak to the violated policy clause for patching by the safety team.

You will score defenses across single-turn and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns with evolving rubrics.