Remote AI Red Team: Adversarial Prompting & Safety

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

Benefits offered by this job

"Remote"

Job summary

AuraOne is seeking a Remote Red Team Specialist to design adversarial prompts, test policy boundaries, and document patch-worthy failures for AI models before deployment.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns while aligning with safety governance. This contractor role requires clear reporting and async collaboration across teams.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication — your reports become the patch ticket.
• 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 Sensitive Advice Boundary Red Team Specialist 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.

Job description

AuraOne is seeking a Remote Red Team Specialist to design adversarial prompts, test policy boundaries, and document patch-worthy failures for AI models before deployment.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns while aligning with safety governance. This contractor role requires clear reporting and async collaboration across teams.