大模型评测产品经理 - AI数据与安全
Core
Design and build evaluation systems and platforms for large language models (LLMs) to drive model iteration and performance improvement.
Role type
Product Manager for AI Model Evaluation & Data
Builds
Evaluation platforms, datasets, and data flywheels for LLMs
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
B2D/platform product experience, requirement abstraction, platform thinking, cross-functional collaboration, data awareness
Preferred skills
LLM evaluation experience, AI tool usage, low-code prototyping
Technologies
LLM Judge, Agent evaluation, data flywheels
Responsibilities
Define evaluation standards and build platform capabilities for model assessment; Collaborate with algorithms and training teams to translate evaluation insights into model improvements; Extract common business problems to create standardized, reusable evaluation features; Analyze model performance data to identify gaps and propose iteration directions.
Seniority
Mid-level, hands-on IC
