AI Red Team Analyst

At Crossing Hurdles, we work as a referral partner. We refer candidates to Mercor that collaborates with the world’s leading AI research labs to build and train cutting-edge AI models.

Organization: Mercor
Position: AI Red-Teamer - Adversarial AI Testing
Referral Partner: Crossing Hurdles
Type: Hourly Contract
Compensation: $54–$111/hour
Location: Remote
Commitment: 10–40 hours/week

Role Responsibilities (Training support will be provided)

• Perform adversarial testing on AI models, including jailbreaks, prompt injections, misuse cases, and exploit discovery.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structured testing methodologies using defined taxonomies, benchmarks, and red-teaming playbooks.
• Produce reproducible documentation, reports, and datasets that customers can act on.
• Support multiple red-teaming projects across different customers and AI safety use cases.
  
  

Requirements

• Strong experience in AI red-teaming, adversarial testing, cybersecurity, or socio-technical risk analysis.
• Ability to think adversarially and push systems to failure points in a structured, methodical way.
• Strong written communication skills to clearly explain risks to technical and non-technical stakeholders.
• Comfort working with sensitive topics such as bias, misinformation, or harmful behaviors (participation optional and supported).
• Adaptability to move across projects, customers, and testing scenarios.
  
  

Application process (Takes 20 min)

• Upload resume
• AI interview based on your resume (15 min)
• Submit form