AI Trainer & Evaluator (AI Product Manager)
TextAs an AI Product Manager, I evaluated and tested AI product features involving Chinese Q&A, text generation, and multi-turn conversations. My role required reviewing large language model (LLM) outputs for factual accuracy, reasoning, safety, and user experience. I optimized prompts and content templates to enhance AI-generated output quality. • Conducted comprehensive evaluation and rating of LLM responses for clarity, correctness, and cultural appropriateness. • Provided written feedback and scoring in structured workflows utilizing industry evaluation criteria. • Refined dataset content and labeling processes to improve training and evaluation reliability. • Utilized proprietary and mainstream AI tools to annotate, review, and document test results.