Adversarial AI Testing Specialist Remote
Mercor • United States
Role & seniority: AI Red Team Specialist (contract/part-time or full-time allowed)
Stack/tools: Adversarial ML, cybersecurity, socio-technical probing; frameworks and benchmarks for testing; documentation practices for reproducible reports
Top 3 responsibilities
-
Evaluate AI models with adversarial inputs to surface vulnerabilities and improve safety
-
Generate high-quality human data by annotating failures and classifying vulnerabilities
-
Document findings reproducibly to create actionable reports and datasets for customers
Must-have skills
-
Fluent in English and Hebrew
-
Experience in AI adversarial work, cybersecurity, or socio-technical probing
-
Strong ability to communicate risks to technical and non-technical stakeholders
Nice-to-haves
-
Experience with Adversarial ML, cybersecurity, or socio-technical risk
-
Creative probing abilities (e.g., psychology or unconventional adversarial thinking)
-
Location & work type: Remote; hourly contractor position paid weekly via Stripe Connect; 20+ hours per week (remote flexibility)
Full Description
About The Job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Position: AI Red Team Specialist
Type: Full-time or Part-time Contract Work
Compensation: $58/hour
Location: Remote
Commitment: 20+ hours/week
Role Responsibilities
Evaluate AI models by probing with adversarial inputs to surface vulnerabilities and enhance safety. Generate high-quality human data by annotating failures and classifying vulnerabilities. Apply structured frameworks and benchmarks to maintain consistent testing. Document findings reproducibly to produce actionable reports and datasets for customers. Collaborate on sensitive topics with clear guidelines and wellness resources.
Qualifications
Must-Have
Fluent in English and Hebrew. Prior experience in AI adversarial work, cybersecurity, or socio-technical probing. Strong communication skills to explain risks to both technical and non-technical stakeholders.
Preferred
Experience with Adversarial ML, Cybersecurity, or Socio-technical risk. Skills in Creative probing such as psychology or unconventional adversarial thinking.
Compensation & Legal
Hourly contractor, Paid weekly via Stripe Connect.
Application Process (Takes 20–30 mins to complete)
Upload resume AI interview based on your resume Submit form
Resources & Support
For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome/welcome
For any help or support, reach out to: support@mercor.com
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
,
