商业化资深评测产品经理（AI Evaluation）-国际化
Core
Design and optimize evaluation systems, metrics, and quality standards for AI Agents, specifically focusing on advertising scenarios.
Role type
Senior Product Manager (AI Evaluation)
Builds
Scalable evaluation workflows, benchmark datasets, and evaluation tool platforms for advertising AI Agents.
Domain
Advertising technology and AI/LLM evaluation
Deliverable
production ML models
Required skills
AI Agent evaluation methodology, LLM understanding, benchmark dataset construction, rubric creation, data annotation processes, cross-functional collaboration
Preferred skills
Experience in advertising or marketing technology, passion for AI-marketing integration
Technologies
LLM frameworks, evaluation tool platforms, experiment tracking systems
Responsibilities
Design AI Agent evaluation metrics and quality standards; Build scalable evaluation processes covering human and model testing; Construct and maintain benchmark datasets for advertising scenarios; Collaborate with R&D to iterate evaluation models; Build tool platforms for experiment tracking and error analysis; Drive product quality improvements through evaluation insights.
