Remote AI Adversarial Security Researcher

AuraOne; United States; On-site; USD 96,000 - 124,000; Full time

Job summary

AuraOne is seeking a CVE Vulnerability Expert to work remotely as an independent contractor in the United States. You will design adversarial prompts to probe AI weaknesses, document failures with reproduction steps, and assign the corresponding policy violations to support patching and regression testing.

You will score defenses in both single-turn and multi-turn conversations, triage new attack vectors with severity, and maintain a library of attack patterns while aligning with the broader

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for CVE Vulnerability Expert 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).
• 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

CVE Vulnerability evaluation

Job description

AuraOne is seeking a CVE Vulnerability Expert to work remotely as an independent contractor in the United States. You will design adversarial prompts to probe AI weaknesses, document failures with reproduction steps, and assign the corresponding policy violations to support patching and regression testing.

You will score defenses in both single-turn and multi-turn conversations, triage new attack vectors with severity, and maintain a library of attack patterns while aligning with the broader