Remote AI Safety Red-Teamer, Arabic STEM PhD

AuraOne; United States; Remote; USD 52,000 - 58,000; Full time

Job summary

AuraOne is seeking a Bilingual Arabic STEM Expert (PhD) for a remote AI Safety red-team track. You will design adversarial prompts, document failures with rigorous reproduction steps, and tie each jailbreak to a policy clause to help patch gaps before a model ships.

This independent contractor role requires strong offense/security research background, clear written reporting, and at least 10 hours per week of async availability.

Qualifications

• Background in offensive security, AppSec, or trust & safety operations.
• Experience publishing or reproducing public adversarial-ML research.
• Multilingual fluency for cross-language attack testing.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Bilingual Arabic STEM Expert (PhD) — AI Safety 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Arabic generalist evaluation

Education

PhD in a relevant field

Job description

AuraOne is seeking a Bilingual Arabic STEM Expert (PhD) for a remote AI Safety red-team track. You will design adversarial prompts, document failures with rigorous reproduction steps, and tie each jailbreak to a policy clause to help patch gaps before a model ships.

This independent contractor role requires strong offense/security research background, clear written reporting, and at least 10 hours per week of async availability.