Remote AI Safety Red Teamer — Adversarial Prompt Expert

AuraOne, Inc.; United States; Remote; USD 96,000 - 116,000; Part time

Benefits offered by this job

Remote work

Contractor engagement

Job summary

AuraOne, Inc. is seeking an AI Safety Red Teamer for a remote contractor role focused on stress-testing AI systems with adversarial prompts. You design attack scenarios, document failures, and tie each jailbreak to a policy clause to drive patches.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns while collaborating with the safety team. Must be able to work asynchronously at least 10 hours per week from US time zones.

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 AI Safety Red Teamer 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

AI Safety Red Teamer evaluation

Job description

AuraOne, Inc. is seeking an AI Safety Red Teamer for a remote contractor role focused on stress-testing AI systems with adversarial prompts. You design attack scenarios, document failures, and tie each jailbreak to a policy clause to drive patches.

You will score defenses, triage new attack vectors, and maintain a library of attack patterns while collaborating with the safety team. Must be able to work asynchronously at least 10 hours per week from US time zones.