Bilingual AI Red Team Specialist (English & Hebrew) | $57.74/hr Remote

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

Type: Hourly contract

Compensation: $57.74/hour

Location: Remote

Commitment: 10–40 hours/week

Role Responsibilities

• Red team conversational AI models and agents, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Generate high-quality human red team data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structured taxonomies, benchmarks, and red-teaming playbooks to ensure consistent and reproducible evaluations.
• Produce clear documentation, including reports, datasets, and attack cases that customers can act upon.
• Identify vulnerabilities that automated testing systems fail to detect.
• Work asynchronously while maintaining high standards of clarity, structure, and accuracy.

Requirements

• Fluent in English and Hebrew (required).
• Prior experience in red teaming, adversarial AI testing, cybersecurity, or socio-technical risk analysis.
• Strong adversarial mindset with the ability to systematically push AI systems to failure points.
• Ability to clearly communicate risks to both technical and non-technical stakeholders.
• Comfortable working independently in a fully remote, contract-based environment.
• Willingness to review sensitive AI outputs, with clear guidelines and wellness support provided.

Preferred Experience

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

Application Process (Takes 20 Min)

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