Mercor is searching for an Internet-Native Bilingual Evaluator Expert (Spanish – Latin America) to evaluate AI model outputs in English and Spanish. The role demands native fluency in Latin American Spanish and professional English skills, along with a strong grasp of internet culture and communication specific to Spanish-speaking countries.

Responsibilities include analyzing content for naturalness and fluency, creating evaluation guidelines, and collaborating with project teams. Candidates will also engage with various digital platforms to understand cultural nuances in language. This is a remote contract position, offering 10–20 hours per week.