Definição
Also called: evals.
Testing what a model can do by having it answer a set of questions and scoring the answers, often by people working from a rubric. “Evals” are those test sets and the scoring runs.
Used in: AI evaluator and rater roles, and expert roles in most fields.
Nas vagas abertas agora
4,412 of the open roles we list mention “evaluation” or a word for it in the title or description, on 59 platforms (as of 3 November 2026). Of those that state an hourly rate (825 distinct postings), the median is $65/hr, and the middle half pay $35 to $100.
A maioria em: Invisible (552), Lilt (373), Alignerr (317), Mercor (274), Handshake AI (240), Ethos (238) e mais 53.
Open Source Maintainer / Core Contributor – Software EngineerMercor·United States·Período integral
Os 10% mais bem pagos recebem:$150/hhá 1 dia
Café Managers: Feedback on a Shift-Handover ProductTerac·Afghanistan·Horário flexível
$42 (pagamento único)há 1 dia
Business Management ConsultantTuring·Local não informado·Período integral
Pagamento não informadohá 1 dia
Finance Expert — AI Training & EvaluationRise Data Labs·No mundo todo
$50–100/hhá 1 dia
Sales and Business Development Expertmicro1·Local não informado
$15–35/hhá 1 dia
English-Speaking AI Image and Video EvaluatorOutlier·Philippines·Horário flexível
Até $7/hhá 3 dias
Termos relacionados
Checagem de fatosChecking each claim in a model's answer against reliable sources and marking what is wrong, unsupported or out of date.Classificação por preferênciaComparing two or more model answers to the same prompt and saying which is better, often with a reason and a rating of how much better.RLHFA way of training a model on people's judgements. ← EQTermo anterior, de A a Z. Fact-checking →Próximo termo, de A a Z. Glossário completoTodos os termos em uma página, de A a Z.Abrir →