Linguists to build the language analysis scenarios frontier AI labs use to test model judgment on syntax, semantics, and phonology. After Query builds the expert evaluation data that frontier AI labs use to measure and improve their models. We're hiring linguists as contractors to author and grade the language analysis scenarios those evaluations run on. Models are made of language, and linguists are unusually well placed to find where their command of it breaks.

What you'll actually do

Author linguistic scenarios that test real analysis, from syntactic ambiguity to semantic entailment to phonological pattern. Write reference analyses with the argumentation behind each judgment, the data, the generalization, the exceptions. Grade model output for analytical accuracy and honest handling of the data. Flag analyses that read plausible but misparse the sentence or mislabel the phenomenon.

Who this is for

Linguists with an advanced degree and at least two years of research, teaching, or applied work. Specialists in any subfield, syntax, semantics, phonology, morphology, sociolinguistics, psycholinguistics, and beyond. Analysts who reason from data to generalization and can say what would falsify their own

📌 Linguistics Expert (España)
🏢 AfterQuery
📍 España