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 Gujarati (Remote Contract)

Test frontier AI models and agents for safety vulnerabilities through adversarial conversations, including jailbreaks, prompt injection, misuse, bias, and manipulation. Create annotated datasets, attack scenarios, and reproducible safety reports in English and Gujarati.

USUnited States
$16 – $22 / hour
RemoteContractMiddleSeniorEnglish RequiredGujarati RequiredArtificial Intelligence
Cyber Security

Description

  • Adversarially test conversational AI models and agents for jailbreaks, prompt injection, misuse, bias exploitation, and multi-turn manipulation
  • Create human-generated data by annotating failures, categorizing vulnerabilities, and identifying systemic risks
  • Use established taxonomies, benchmarks, and playbooks to maintain consistent evaluations
  • Develop reproducible reports, datasets, and attack scenarios
  • Assess AI outputs involving sensitive subjects, including bias, misinformation, and harmful behavior
  • Identify weaknesses that automated evaluation methods fail to detect
  • Broaden evaluation coverage to help limit unexpected production issues
  • Improve customer AI systems through structured adversarial testing

Requirements

  • Native-level fluency in both English and Gujarati
  • Sound judgment when evaluating language and content
  • Ability to determine whether AI responses are accurate, complete, and appropriate, and to explain the assessment
  • Careful attention to subtle errors, inconsistencies, and omissions
  • Consistent use of taxonomies, benchmarks, playbooks, guidelines, and quality standards
  • Ability to communicate reasoning clearly to technical and non-technical audiences
  • Flexibility to work across different projects, task formats, and customers
  • Preferred background in adversarial machine learning, cybersecurity, socio-technical risk, or creative AI probing
  • Must work as an independent contractor
  • H-1B and STEM OPT candidates are not supported

Benefits

  • Fully remote position
  • Flexible scheduling with the ability to choose your own working hours
  • Weekly payments through Stripe or Wise
  • Projects may be extended, shortened, or ended early based on business needs and performance
  • Optional participation in projects involving higher-sensitivity content
  • Defined guidance and wellness resources for sensitive-content assignments
  • Reasonable accommodations available upon request
  • Chance to develop experience in human-data-driven AI red teaming
  • Work alongside leading researchers
  • Referral payments of up to $90 per successful referral, subject to applicable limits

Related Jobs