AI Data Labeling / Model Evaluation Candidate — Annotation QA, intent classification, and evaluation
Performed annotation QA and model response evaluation by reviewing AI outputs for relevance and completeness. Applied consistent labeling guidelines for intent classification and business workflow understanding. Documented edge cases and uncertain items for later review with clear evidence. • Reviewed structured records for clarity, completeness, and factual consistency • Classified ambiguous user intent and task/business scenario • Tracked workflow status and logged uncertain cases for evaluation • Wrote Chinese-English edge case notes and evaluation reports