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 Team Expert (English and Punjabi)

Mercor is seeking an English- and Punjabi-speaking AI safety expert to red-team conversational models and agents. The contract role focuses on uncovering vulnerabilities, creating attack cases, and producing reproducible safety reports for AI research customers.

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

Description

  • Test conversational AI models and agents with jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation
  • Evaluate model outputs on sensitive subjects, including bias, misinformation, and harmful behavior
  • Document failures, categorize vulnerabilities, and identify systemic risks
  • Use established taxonomies, benchmarks, and playbooks to maintain consistent evaluations
  • Create reproducible reports, datasets, and attack cases for customers
  • Investigate AI systems for weaknesses that automated testing may overlook
  • Broaden evaluation coverage to help limit unexpected issues in production
  • Improve customer AI systems through human-led, data-driven red teaming

Requirements

  • Native or fluent English and Punjabi proficiency
  • Strong judgment when evaluating language and content
  • Ability to determine whether AI responses are accurate, complete, and appropriate, and explain the assessment
  • Meticulous attention to subtle errors, inconsistencies, and omissions
  • Consistent adherence to testing guidelines and quality standards
  • Ability to communicate reasoning clearly to both technical and non-technical audiences
  • Flexibility to work across projects, task formats, and customers
  • Availability to engage as an independent contractor
  • Must not require H-1B or STEM OPT support
  • Preferred expertise may include adversarial machine learning, jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, harassment or disinformation probing, abuse analysis, conversational AI testing, psychology, acting, or writing

Benefits

  • Work remotely from anywhere permitted by the role
  • Set your own working schedule
  • Receive weekly payments through Stripe or Wise for services provided
  • Projects may be extended, reduced, or ended early based on business needs and performance
  • Access wellness resources and clear guidance for higher-sensitivity projects
  • Build experience in human data-driven AI red teaming
  • Help make AI systems more robust, safe, and trustworthy
  • Competitive compensation
  • Collaborate with leading AI researchers

Related Jobs