Remote Adversarial Prompt Expert - Contractor

AuraOne; United States; On-site; USD 82,656 - 137,760; Full time

Job summary

AuraOne seeks an Adversarial Prompt Expert to remotely stress-test AI systems against adversarial prompts. You will craft attack scenarios, document failures with rigor, and pair each jailbreak with the violated rubric clause for patching gaps.

As a contractor, you will score defenses in both single-turn and multi-turn chats, triage new vectors, and maintain a library of attack patterns to evolve red-team rubrics. 10+ hours weekly, US remote work.

Qualifications

• Experience red‑teaming AI systems or adversarial ML 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).
• 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

Adversarial prompt testing

AI model evaluation

Analytical thinking

Data annotation

Literacy

Presentation development

Job description

AuraOne seeks an Adversarial Prompt Expert to remotely stress-test AI systems against adversarial prompts. You will craft attack scenarios, document failures with rigor, and pair each jailbreak with the violated rubric clause for patching gaps.

As a contractor, you will score defenses in both single-turn and multi-turn chats, triage new vectors, and maintain a library of attack patterns to evolve red-team rubrics. 10+ hours weekly, US remote work.