Adversarial AI Safety Researcher (Remote)

AuraOne, Inc.; United States; Remote; USD 110,000 - 207,000; Full time

Job summary

AuraOne, Inc. is seeking a Remote Child & Adolescent Mental Health Clinical Advisor (AI Safety Benchmark Project) to stress-test AI systems with adversarial prompts. This CONTRACTOR role emphasizes rigorous failure documentation, policy taxonomy, and cross-turn evaluation.

You will design jailbreak-style prompts, document failures, score defenses, and triage emerging vectors, with async availability of at least 10 hours weekly.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Child & Adolescent Mental Health Clinical Advisor (AI Safety Benchmark Project) work.
• Strong written communication — your 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) for Child & Adolescent Mental Health Clinical Advisor (AI Safety Benchmark Project) 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

Child Adolescent Mental Health Clinic

Job description

AuraOne, Inc. is seeking a Remote Child & Adolescent Mental Health Clinical Advisor (AI Safety Benchmark Project) to stress-test AI systems with adversarial prompts. This CONTRACTOR role emphasizes rigorous failure documentation, policy taxonomy, and cross-turn evaluation.

You will design jailbreak-style prompts, document failures, score defenses, and triage emerging vectors, with async availability of at least 10 hours weekly.