Literature Expert for AI Evaluation

Create evaluation materials that test whether AI models can read and interpret literature with care. Your work focuses on grounding interpretations in the text and spotting fluent answers that miss its meaning or craft.

• Write literary scenarios that test passage analysis, form, voice, literary tradition, and other parts of close reading.
• Prepare reference readings that support each claim with specific evidence from the text.
• Rate AI responses for textual accuracy, depth of interpretation, and awareness of literary craft.
• Identify subtle errors and readings that overlook what the text says.

What it pays and takes

• $50 to $100 per hour, paid weekly through Stripe.
• Commit to 20+ hours per week; the work is fully asynchronous.
• Remote role open to candidates in eligible countries.
• Advanced degree in literature, English, comparative literature, or a closely related field.
• At least two years of teaching, research, editorial, or published literary experience.
• Close-reading expertise across periods, genres, or traditions; clear written English, strong prose, and the ability to assess literary craft.
• Peer-reviewed publications, editorial or creative writing, or experience reading literature beyond English are helpful.
• Independent contractor role.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training uses human-written examples and judgments to help models learn and improve. Literary experts are paid for the close reading and careful explanations needed to tell genuine textual understanding from answers that only sound convincing.