Safety Red-Teamer (English & Arabic) | $32.25/hr Remote

Position: AI Red-Teamer — Adversarial AI Testing (Advanced); English & Arabic

Type: Hourly contract

Compensation: $32.25/hour

Location: Remote

Commitment: 10–40 hours/week

Role Responsibilities

• Red team conversational AI models and agents (jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation).
• Generate high-quality red team data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structured taxonomies, benchmarks, and playbooks for consistent evaluation.
• Produce reproducible documentation including reports, datasets, and attack cases.
• Identify vulnerabilities missed by automated testing.

Requirements

• Fluent in English and Arabic (required).
• Prior experience in red teaming, adversarial AI, cybersecurity, or socio-technical risk analysis.
• Strong adversarial and analytical mindset with structured testing approaches.
• Ability to clearly communicate risks to technical and non-technical stakeholders.
• Comfortable reviewing sensitive AI-generated content (with guidelines and wellness support provided).

Preferred Experience

• Adversarial ML (jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction).
• Cybersecurity (penetration testing, exploit development, reverse engineering).
• Socio-technical risk analysis (harassment, misinformation, abuse probing).
• Creative adversarial thinking (psychology, writing, acting, scenario design).

Application Process (Takes 20 Min)

• Upload resume
• Interview (15 min)
• Submit form