混元VLM测评算法工程师（深圳/北京）
Core
Build and maintain a comprehensive evaluation framework for multimodal large models covering object recognition, agents, GUI, STEM, code, and video to establish industry standards.
Role type
Senior IC multimodal large model evaluation engineer
Builds
Automated evaluation pipelines and robust evaluation methods for multimodal large models
Domain
Artificial Intelligence / Multimodal Large Models
Deliverable
production ML models
Required skills
Multimodal large model evaluation, automated evaluation pipeline design, model performance analysis, C/C++, Python, problem-solving
Preferred skills
BMK paper experience, BMK construction experience, research in speech or machine learning
Technologies
C/C++, Python
Responsibilities
Design and build automated evaluation workflows, analyze model capabilities to drive iterative improvements, track industry evaluation trends, establish scientific evaluation frameworks
Seniority
Senior, hands-on IC