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 Red Teaming Expert (English and Punjabi)

Conduct adversarial testing of conversational AI models and agents in English and Punjabi. Create vulnerability annotations, attack cases, datasets, and reproducible safety reports for Mercor’s human-data AI safety projects.

USUnited States
$16 – $22 / hour
RemoteContractMiddleSeniorEnglish RequiredPanjabi RequiredArtificial Intelligence

Description

  • Probe conversational AI models and agents with jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation
  • Create human-data annotations by documenting failures, categorizing vulnerabilities, and identifying systemic risks
  • Use established taxonomies, benchmarks, and playbooks to maintain consistent evaluations
  • Deliver reproducible reports, datasets, and attack cases for customers
  • Assess AI outputs related to bias, misinformation, harmful behavior, and other sensitive subjects
  • Broaden evaluation coverage to identify vulnerabilities that automated testing may overlook
  • Help improve the safety, robustness, and trustworthiness of customer AI systems

Requirements

  • Native or fluent English and Punjabi language skills
  • Sound judgment when evaluating the accuracy, completeness, and appropriateness of AI-generated content
  • Ability to detect nuanced errors, inconsistencies, and omissions
  • Consistent adherence to guidelines, taxonomies, benchmarks, playbooks, and quality standards
  • Clear communication of reasoning to both technical and non-technical audiences
  • Flexibility across projects, task formats, and customer requirements
  • Ability to work as an independent contractor
  • H1-B and STEM OPT candidates are not supported
  • Helpful background in adversarial machine learning, jailbreak datasets, prompt-injection or RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, harassment or disinformation probing, abuse analysis, conversational AI testing, psychology, acting, or unconventional adversarial writing

Benefits

  • Fully remote work with flexible, self-managed scheduling
  • Weekly payments through Stripe or Wise
  • Competitive compensation
  • Wellness resources and clear guidance for higher-sensitivity projects
  • Reasonable accommodations available upon request
  • Referral payments of up to $90 for each successful referral
  • Collaboration opportunities with leading researchers
  • Hands-on experience with human-data AI red teaming at the frontier of AI safety

Related Jobs