This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more.

Role Description

This role involves supporting a leading AI lab in identifying vulnerabilities and improving the safety of advanced conversational AI systems.

• Conduct adversarial testing of conversational AI systems
• Identify vulnerabilities such as jailbreaks, prompt injections, misuse cases, and bias exploitation
• Evaluate AI responses across multi-turn conversations and manipulation scenarios
• Annotate model failures and classify vulnerability types
• Generate structured reports, attack cases, and reproducible datasets
• Follow testing frameworks, taxonomies, and benchmarks to ensure consistency
• Produce clear documentation that helps teams strengthen AI safety systems

Qualifications

• Native-level fluency in English and Hebrew
• Experience in AI red teaming, adversarial machine learning, or cybersecurity
• Background in penetration testing, exploit development, or vulnerability analysis
• Strong analytical thinking and structured problem-solving abilities
• Ability to clearly explain risks to technical and non-technical audiences
• Excellent written communication and attention to detail
• Comfort working across multiple projects and testing scenarios

Requirements

• Experience with adversarial ML techniques (prompt injection, jailbreak testing, RLHF attacks)
• Cybersecurity background in penetration testing or reverse engineering
• Socio-technical risk analysis (bias, misinformation, abuse detection)
• Creative adversarial thinking using psychology, narrative, or behavioral probing

Benefits

• Contribute directly to improving the safety and robustness of advanced AI systems
• Work on frontier AI red-teaming projects with leading AI research teams
• Help identify vulnerabilities before AI systems reach production environments
• Flexible remote project work with competitive compensation

Contract Details

• Independent contractor role
• Fully remote and flexible scheduling
• Geographic eligibility restricted to USA or Israel
• Compensation: $57.74 per hour
• Weekly payments via Stripe or Wise
• Projects may extend or adjust depending on scope and performance
• No access to confidential employer or institutional data required

About the Platform

This opportunity is available through a leading AI-driven work platform.