LogoFresh Jobs Ahead
Mercor
Mercor
51 – 200 Employees
Mercor’s available profile does not include enough verified information about its products, services, customers, sector, or hiring focus to support an accurate company overview. More source material is needed before describing the business or its opportunities.
LinkedIn
Company Jobs

AI Safety Expert, English and Dutch (Remote Contract)

Mercor is seeking English- and Dutch-speaking AI safety experts to red-team conversational models and agents. The work involves creating vulnerability data, attack scenarios, and reproducible safety reports for frontier AI development.

USUnited States
$48 – $62 / hour
RemoteContractMiddleSeniorEnglish RequiredDutch RequiredArtificial Intelligence
Cyber Security

Description

  • Test conversational AI models and agents using jailbreaks, prompt injection, misuse scenarios, bias exploitation, and multi-turn manipulation
  • Create human-generated data by annotating failures, classifying vulnerabilities, and identifying systemic risks
  • Use taxonomies, benchmarks, and playbooks to support consistent safety testing
  • Develop reproducible reports, datasets, and attack cases for customers
  • Find vulnerabilities that automated testing may overlook
  • Broaden evaluation coverage to help reduce unexpected production risks
  • Work with leading researchers to train and improve frontier AI systems

Requirements

  • Native fluency in English and Dutch
  • Previous experience with AI red teaming, cybersecurity adversarial work, or socio-technical probing
  • Ability to test AI systems adversarially and drive them toward failure conditions
  • Experience applying frameworks or benchmarks to structured testing
  • Ability to communicate risks clearly to technical and non-technical audiences
  • Ability to adapt across different projects and customers
  • Adversarial machine learning experience with jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction is preferred
  • Cybersecurity experience in penetration testing, exploit development, or reverse engineering is preferred
  • Socio-technical risk experience involving harassment or disinformation probing, abuse analysis, or conversational AI testing is preferred
  • Creative probing experience in psychology, acting, or writing is preferred
  • Must be able to work as an independent contractor
  • H-1B and STEM OPT candidates are not supported

Benefits

  • Fully remote work
  • Flexible scheduling with the ability to set your own hours
  • Weekly payments through Stripe or Wise based on services delivered
  • Projects may be extended, shortened, or ended early based on business needs and performance
  • Participation in higher-sensitivity projects is optional
  • Content guidelines and wellness resources are provided
  • Reasonable accommodations are available upon request
  • Competitive hourly pay
  • Referral opportunity of up to $250 per successful referral, subject to limits

Related Jobs