Remote AI Adversarial Security Engineer | Jailbreak Testing

AuraOne, Inc.; United States; On-site; USD 55,000 - 110,000; Full time

Benefits offered by this job

Remote — US-eligible

Contractor engagement

Job summary

AuraOne, Inc. seeks a Cybersecurity Engineer — Adversarial Review & AI Security Evaluation to stress-test AI systems through remote contractor work. You will craft adversarial prompts, document failures with rigorous reproduction steps, and map each jailbreak to the violated rubric to help patch gaps.

Responsibilities include scoring defenses, triaging new attack vectors, and maintaining a red-team pattern library. Remote — US-eligible; hourly rate determined after interview.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication; reports become patch tickets.
• Ability to document what was attempted and why in policy-grey areas.
• Familiarity with jailbreak, prompt-injection, and policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts that probe weakness classes for assignments.
• Document every successful attack with reproduction steps and violated policy clause.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route to safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new rubrics.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Cyber security evaluation

Job description

AuraOne, Inc. seeks a Cybersecurity Engineer — Adversarial Review & AI Security Evaluation to stress-test AI systems through remote contractor work. You will craft adversarial prompts, document failures with rigorous reproduction steps, and map each jailbreak to the violated rubric to help patch gaps.

Responsibilities include scoring defenses, triaging new attack vectors, and maintaining a red-team pattern library. Remote — US-eligible; hourly rate determined after interview.