Adversarial Prompt Security Evaluator (Remote)

AuraOne; United States; On-site; USD 82,656 - 165,312; Part time

Job summary

AuraOne is seeking a Prompt Injection Security Evaluator for a remote contractor engagement. You will design adversarial prompts and assess AI systems against jailbreak and policy-bypass scenarios, reporting failures with clear reproduction steps.

You will score defenses across one- and multi-turn conversations, triage emerging vectors, and maintain a library of attack patterns. Strong documentation and communication are essential to help patch gaps before deployment.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.
• 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.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Prompt Injection Security Evaluator 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Prompt injection security

Security review

Adversarial testing

Threat modeling

Job description

AuraOne is seeking a Prompt Injection Security Evaluator for a remote contractor engagement. You will design adversarial prompts and assess AI systems against jailbreak and policy-bypass scenarios, reporting failures with clear reproduction steps.

You will score defenses across one- and multi-turn conversations, triage emerging vectors, and maintain a library of attack patterns. Strong documentation and communication are essential to help patch gaps before deployment.