Multilingual AI Evaluation Specialist

Blueprint is seeking detail-oriented Labelers / Annotators in Mendoza, Argentina, to evaluate AI-generated responses across multiple languages. The role involves performing side-by-side evaluations and requires fluency in English along with at least one other language such as Chinese, Japanese, or German.

Applicants should have strong analytical skills and experience in annotation to maintain high-quality evaluations of outputs from various AI models.