AI Safety Expert – English, Finnish

Posted 12hrs ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

AI safety experts red-teaming conversational AI models for Mercor, which partners with leading labs to train frontier systems. Producing reproducible vulnerability data and attack cases.

Responsibilities:

  • Red-team conversational AI models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
  • Annotate failures, classify vulnerabilities, and flag systemic risks
  • Follow taxonomies, benchmarks, and playbooks to keep testing consistent
  • Produce reproducible reports, datasets, and attack cases
  • Probe AI outputs involving bias, misinformation, or harmful behaviors
  • Expand evaluation coverage and uncover vulnerabilities automated tests miss
  • Collaborate on projects training and enhancing frontier AI systems

Requirements:

  • Fluent/native fluency in English and Finnish
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
  • Experience probing AI systems adversarially
  • Ability to use frameworks, taxonomies, benchmarks, and playbooks
  • Ability to explain risks clearly to technical and non-technical stakeholders
  • Adaptability across projects and customers
  • Independent contractor status
  • Must be able to work without access to confidential or proprietary information from another employer, client, or institution
  • H1-B and STEM OPT candidates are not supported

Benefits:

  • Fully remote role
  • Flexible, own schedule
  • Higher-sensitivity projects are optional
  • Clear guidelines and wellness resources
  • Weekly payments via Stripe or Wise
  • Competitive payment
  • Referral opportunity earning up to $250 per successful referral
  • Reasonable accommodations upon request