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

Remote AI Safety Expert (English and Marathi) at Mercor

Probe conversational AI models for vulnerabilities through red-team testing in English and Marathi. Create reproducible datasets, attack cases, and reports for human-data AI safety projects.

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

Description

  • Conduct red-team testing of conversational AI models and agents using jailbreaks, prompt injection, misuse scenarios, bias exploitation, and multi-turn manipulation
  • Create human data by annotating failures, categorizing vulnerabilities, and identifying systemic risks
  • Use taxonomies, benchmarks, and playbooks to maintain consistent evaluations
  • Develop reproducible reports, datasets, and attack cases for customers
  • Assess AI outputs involving sensitive subjects, including bias, misinformation, and harmful behavior
  • Identify weaknesses that automated testing may overlook
  • Broaden evaluation coverage to help prevent unexpected production issues
  • Support customers in improving the safety, robustness, and trustworthiness of their AI systems

Requirements

  • Fluent or native English and Marathi language skills are required
  • Sound judgment about language and content, including the ability to evaluate whether AI responses are accurate, complete, and appropriate and explain the reasoning
  • Exceptional attention to subtle errors, inconsistencies, and omissions
  • Consistent adherence to established guidelines and quality standards
  • Clear communication of reasoning to both technical and non-technical audiences
  • Ability to adapt across projects, task formats, and customers
  • Must work as an independent contractor
  • H1-B and STEM OPT candidates are not supported
  • Preferred: adversarial machine learning experience with jailbreak datasets, prompt injection, RLHF or DPO attacks, or model extraction
  • Preferred: cybersecurity experience in penetration testing, exploit development, or reverse engineering
  • Preferred: socio-technical risk experience involving harassment or disinformation probing, abuse analysis, or conversational AI testing
  • Preferred: psychology, acting, or writing experience that supports unconventional adversarial thinking

Benefits

  • Fully remote work
  • Flexible scheduling with the ability to choose your working hours
  • Weekly payments through Stripe or Wise based on services delivered
  • Project duration may be extended, shortened, or ended early according to business needs and performance
  • Wellness resources and clear guidance for projects involving higher-sensitivity content
  • Reasonable accommodations available upon request
  • Referral program offering up to $90 for each successful referral, with no limit on referrals
  • Opportunity to collaborate with leading researchers
  • Experience conducting human-data-driven AI red teaming at the forefront of AI safety

Related Jobs