Back to all jobs
AI

AI Research Generalist – Model Evaluation

Remote – Global Part-time Platform: Mercor USD 40–80 / hour Worldwide
Apply directly on the partner platform.

About the Role

A specialized AI research initiative focused on benchmarking and improving advanced language models through structured research, high-quality question development, and evaluation material creation. The work involves supporting model training and assessment through accurate, well-organized, and research-driven content.

This opportunity is ideal for individuals with 2–3 years of relevant professional experience in STEM or non-STEM disciplines, or postgraduate students pursuing or recently completing master's-level studies. Candidates should demonstrate strong online research abilities, critical thinking, and the ability to communicate complex information clearly.

The work involves developing research questions, preparing accurate answers, gathering information from diverse sources, and creating structured evaluation materials for AI systems. Research accuracy, clarity, independent judgment, and consistent technical execution are critical.

What You'll Do

  • Develop high-quality research questions for advanced AI model training.
  • Prepare accurate and well-structured answers across multidisciplinary subject areas.
  • Create evaluation materials to assess language model performance.
  • Conduct online research using credible and relevant information sources.
  • Gather, verify, and synthesize information from multiple sources.
  • Summarize complex findings into clear and accessible written content.
  • Evaluate AI-generated responses for factual accuracy, reasoning, and completeness.
  • Identify inconsistencies, errors, and gaps in model-generated outputs.
  • Maintain consistency and quality across research and evaluation deliverables.
  • Complete assigned research tasks within agreed project timelines.

Requirements

  • Bachelor's degree from a recognized academic institution, combined with 2–3 years of relevant professional experience, or current/recent enrollment in a master's degree program.
  • Background in STEM, non-STEM, or interdisciplinary academic fields.
  • Strong online research and information-gathering skills.
  • Excellent written communication and analytical abilities.
  • Ability to synthesize information from diverse sources.
  • Strong critical thinking and independent problem-solving skills.
  • Ability to create structured research questions, answers, and evaluation materials.
  • High attention to detail and commitment to research accuracy.
  • Ability to work independently in a fully remote environment.
  • Availability for approximately 10–20 hours per week.
  • Must own a MacBook or Mac computer with an Apple M-series chip or Intel processor.
  • Must have macOS 15 or higher installed on the required Mac device.
  • Ability to begin work immediately or within a short onboarding period.
  • Postgraduate qualifications or an interdisciplinary academic background are preferred.
  • Previous experience in AI evaluation, language model benchmarking, research writing, or data annotation is preferred.
Application Note: By submitting your profile for this partnered position, our team can quickly review your background and reach out to present you with this specific opportunity or match you with similar AI Training projects.