Remote Adversarial AI Security Researcher

AuraOne; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

AuraOne seeks a Cybersecurity Research Expert - Offensive Security & Vulnerability Research for a remote role to stress-test AI systems against adversarial prompts and document failures with rubric violations for patching.

You design prompts, document attacks with reproduction steps, score defenses, triage emerging vectors, and maintain a library of attack patterns to improve safety across AI deployments.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication; reports become patch tickets.
• Comfort documenting what was attempted and why.
• Familiarity with prompt-injection, jailbreak and policy-bypass concepts.

Responsibilities

• Design adversarial prompts probing known weakness classes for AI systems.
• 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 them to safety teams with severity tags.
• Maintain a personal library of attack patterns and propose new rubrics.
• Calibrate against the red-team cohort to keep coverage and severity consistent.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Job description

AuraOne seeks a Cybersecurity Research Expert - Offensive Security & Vulnerability Research for a remote role to stress-test AI systems against adversarial prompts and document failures with rubric violations for patching.

You design prompts, document attacks with reproduction steps, score defenses, triage emerging vectors, and maintain a library of attack patterns to improve safety across AI deployments.