AI Safety & Red-Team Specialist

At a glance

• $60 – $90 / hourPaid in USD, weekly. Rate set after a short paid assessment.
• Remote, any timezoneWork from anywhere with a stable connection.
• Hourly contract · paid weekly in USD · remoteChoose your own hours.
• Ongoing, project-based Starts when a matching project opens · Rolling applications
• Contract · Senior reviewMultiple openings · Client: AI labs and data vendors

What you will do

• Design adversarial prompts in your specialty: CBRN, cyber threat intelligence, OSINT, child safety.
• Run jailbreak and prompt-injection tests and document successful attacks.
• Grade model answers for harmful uplift against safety rubrics.
• Arabic track: safety evaluation of Arabic model outputs.

What we are looking for

• One or more of: chemical, biological, radiological, nuclear or explosives safety background (3+ years); cyber threat intelligence practice; multilingual OSINT or web-intelligence analysis; hands-on LLM red-teaming; child-safety research or trust and safety work.
• Sound judgement with sensitive material.

Nice to have

• Native Arabic.
• Relevant certifications (for example GIAC, OSCP, CIH).
• Published safety research.

Hiring process

1. Step 1Profile and CV review
2. Step 2AI interview in English or Arabic, proctored (about 20 minutes)
3. Step 3Identity check: government ID and liveness
4. Step 4Credential and employment verification
5. Step 5Short paid assessment and Expert Score

Free to apply. Vettedlance never charges candidates, and will never ask you to pay for training, tests or equipment.