Humanities Researcher for AI Model Evaluation

Help improve next-generation AI systems by creating rigorous humanities evaluations grounded in interpretation, argument, context, and analytical reasoning. This remote contractor opportunity relies on your subject-matter expertise, no prior AI experience required. Key Responsibilities

• Create original, high-difficulty question-and-answer pairs that challenge advanced AI models.
• Research, verify, and cite primary texts and reputable sources to support accurate answers and reasoning.
• Develop prompts that require deep analysis or interpretation rather than simple factual recall.
• Test questions with AI models and refine them for difficulty, clarity, and correctness.
• Produce precise, unambiguous questions and well-supported answers.
• Incorporate reviewer feedback and follow project quality standards.

• Advanced academic background or professional experience in history, literature, philosophy, linguistics, classics, art history, journalism, or another humanities discipline.
• Strong research and source-triangulation skills, analytical thinking, close reading, and analytical writing ability.
• Excellent attention to detail, written precision, and ability to document reasoning and sources clearly.
• Experience writing nuanced questions that assess understanding beyond surface-level facts.
• Self-direction and reliability when completing remote work independently.
• Experience evaluating or training AI models is helpful but not required.

• Remote, independent contractor engagement.
• Work is paid by qualifying task, and time needed may vary by experience and workflow.
• Minimum weekly task-submission requirements apply.

$40 to $90 per hour equivalent, with payment based on tasks that meet project specifications.

• Open roles are typically filled within 48 hours, so applicants should be ready to begin promptly.
• If selected, complete onboarding and begin initial tasks within 24 to 48 hours.