AI Safety Expert – English, Assamese

Posted 8hrs ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

AI safety red-teamer probing conversational models for Mercor’s frontier AI projects. Generating adversarial datasets, vulnerability reports, and attack cases to strengthen AI systems.

Responsibilities:

  • Red-team conversational AI models and agents using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
  • Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
  • Apply taxonomies, benchmarks, and playbooks to maintain consistent testing
  • Produce reproducible reports, datasets, and attack cases for customers
  • Review AI outputs involving sensitive topics such as bias, misinformation, and harmful behaviors
  • Uncover vulnerabilities that automated tests miss
  • Expand evaluation coverage and reduce production surprises
  • Strengthen customer AI systems and contribute to safer, more trustworthy AI

Requirements:

  • Native fluency in English and Assamese
  • Prior red teaming experience, including AI adversarial work, cybersecurity, or socio-technical probing
  • Ability to probe systems adversarially and push them to breaking points
  • Experience using frameworks or benchmarks for structured testing
  • Ability to explain risks clearly to technical and non-technical stakeholders
  • Ability to adapt across projects and customers
  • Nice-to-have specialties: adversarial ML, jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, harassment/disinformation probing, abuse analysis, conversational AI testing, psychology, acting, or writing
  • Must not be an H1-B or STEM OPT candidate

Benefits:

  • Fully remote role that can be completed on your own schedule
  • Weekly payments via Stripe or Wise based on services rendered
  • Participation in higher-sensitivity projects is optional
  • Clear guidelines and wellness resources for sensitive-content projects
  • Competitive pay
  • Referral earnings of up to $90 per successful referral, with no limit on referrals (restrictions may apply)