大模型评估产品经理（J82456）
Core
Define evaluation standards for large language models (Q&A, creative content, information processing) and analyze results to guide model and system strategy optimization.
Role type
Product Manager for Large Model Evaluation
Builds
Evaluation standards, analysis insights, and automated evaluation tools
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
Evaluation standard formulation, deep analysis of evaluation results, product iteration collaboration, competitive analysis, automated evaluation tool design
Preferred skills
User behavior research, business analysis, strong writing sense, pattern recognition, technical sensitivity to deep learning and machine learning, structured thinking
Technologies
Large Language Models, Deep Learning, Machine Learning, NLP, Dialogue Robots
Responsibilities
Establish evaluation standards for LLMs, analyze evaluation results to guide optimization, collaborate with product and engineering teams, conduct market and competitor analysis, design automated evaluation tools
Seniority
Mid-level, hands-on IC
