التعريف
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.
في الوظائف المفتوحة حاليًا
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.
معظمها على: Invisible (552)، Lilt (373)، Alignerr (317)، Mercor (274)، Handshake AI (240)، Ethos (238)، و53 أخرى.
Open Source Maintainer / Core Contributor – Software EngineerMercor·United States·دوام كامل
أعلى 10% أجرًا:$150/ساعةمنذ 1 يوم
Café Managers: Feedback on a Shift-Handover ProductTerac·Afghanistan·ساعات مرنة
$42 (دفعة واحدة)منذ 1 يوم
Business Management ConsultantTuring·الموقع غير محدد·دوام كامل
الأجر غير محددمنذ 1 يوم
Finance Expert — AI Training & EvaluationRise Data Labs·أي بلد
$50–100/ساعةمنذ 1 يوم
Sales and Business Development Expertmicro1·الموقع غير محدد
$15–35/ساعةمنذ 1 يوم
English-Speaking AI Image and Video EvaluatorOutlier·Philippines·ساعات مرنة
حتى $7/ساعةمنذ 3 أيام
مصطلحات ذات صلة
التحقق من الحقائقChecking each claim in a model's answer against reliable sources and marking what is wrong, unsupported or out of date.ترتيب التفضيلاتComparing two or more model answers to the same prompt and saying which is better, often with a reason and a rating of how much better.RLHFA way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. ← EQالمصطلح السابق، من A إلى Z. Fact-checking →المصطلح التالي، من A إلى Z. المسرد الكاملكل المصطلحات في صفحة واحدة، من A إلى Z.فتح →