Bilingual Arabic STEM Expert (PhD) — AI Safety

AuraOne; United States; Presencial; USD 52 000 - 58 000; Tempo integral

Resumo da oferta

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.

Qualificações

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

Responsabilidades

• 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.

Conhecimentos

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Arabic generalist evaluation

Formação académica

PhD in a relevant field

Descrição da oferta de emprego

About the role

Bilingual Arabic STEM Expert (PhD) — AI Safety is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.
Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.
Push on refusal boundaries and dual-use risk before a model ships.

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.
  Track Adversarial evaluation Work model Remote · Independent specialist contractor Compensation $38–$42 / hr Eligible from US

What you should bring

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Bilingual Arabic STEM Expert (PhD) — AI Safety 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.

Role signals

Example tasks

• Construct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.
• Score a model's defenses against a known jailbreak pattern across 20 variants.
• Propose a new red-team rubric category after spotting an emerging attack vector.
• Reproduce a failure another reviewer reported and confirm the severity tag.

Useful experience

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

Compensation and schedule

$38–$42 / hr
Expected arrangement: contractor , with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

• Adversarial prompting
• Red-team analysis
• Policy taxonomy
• Failure documentation
• Arabic generalist evaluation