Remote Adversarial AI Security Evaluator (Jailbreak Focus)

AuraOne; United States; On-site; USD 55,104 - 96,432; Full time

Job summary

AuraOne is seeking a Jailbreak Exploit Security Evaluator contractor to help harden AI systems by thinking like attackers, documenting failures with rigor, and patching gaps before deployment.

You will design adversarial prompts, document attack steps and violated policies, and score defenses across turn-based conversations, ensuring safe model behavior and robust defenses for customers.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, 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) for Jailbreak Exploit 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.
• 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 evaluation

Security review

Adversarial testing

Threat modeling

Jailbreak

Exploit

Job description

AuraOne is seeking a Jailbreak Exploit Security Evaluator contractor to help harden AI systems by thinking like attackers, documenting failures with rigor, and patching gaps before deployment.

You will design adversarial prompts, document attack steps and violated policies, and score defenses across turn-based conversations, ensuring safe model behavior and robust defenses for customers.