AI Model Evaluator / Data Annotation Contributor
I evaluated LLM outputs using detailed rubrics focused on factors such as instruction following, fact-checking, completeness, verbosity, and writing style. I conducted quality and accuracy checks for STEM and mathematical reasoning, translation validation, and prompt adherence in both English and Spanish contexts. I completed high-volume workflows involving text, email, and document annotation, anonymization of PII, and multilingual QA assessment. • Performed evaluation of prompt-following, hallucination, and factually accurate responses for LLM model output. • Verified and scored mathematical reasoning and solution logic across STEM tasks. • Conducted English-Spanish translation and localization QA for AI-generated text. • Managed PII removal, metadata review, and categorization of emails and documents.