AI Humanities Evaluator: Research & Model Critique

Mercor; San Francisco (CA); Presencial; USD 62.000 - 83.000; Jornada completa

Descripción de la vacante

Mercor maintains a standing humanities pool for AI training and evaluation. This listing is not a single opening but a continuously open pool that matches scholars to projects when needed. New projects can start on short notice, and the rate is posted per project, typically between $45 and $60 per hour.

If you have a graduate degree in humanities or equivalent scholarly experience, you can join. Work involves writing questions, grading model outputs, and flagging misinterpretations, with

Formación

• Graduate degree in a humanities field or equivalent scholarly or professional experience.
• Clear written communication, since most of the work involves explaining your reasoning
• Comfort with ambiguous tasks, and willingness to flag unclear instructions

Responsabilidades

• Write a question from your field, with sources, context, and the interpretive problem, plus the reference answer a model's attempt gets graded against.
• Grade model-written interpretation and argument: check sources, reasoning, and context for accuracy.
• Flag when a model produces fluent prose that misreads text, ignores debate, or invents a citation.

Conocimientos

Clear written communication

Ambiguity tolerance

Scholarly judgment

Educación

Graduate degree in humanities

Descripción del empleo

Mercor maintains a standing humanities pool for AI training and evaluation. This listing is not a single opening but a continuously open pool that matches scholars to projects when needed. New projects can start on short notice, and the rate is posted per project, typically between $45 and $60 per hour.

If you have a graduate degree in humanities or equivalent scholarly experience, you can join. Work involves writing questions, grading model outputs, and flagging misinterpretations, with