AI Frameworks Engineer - Model and Kernel Optimization
Shanghai
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningEducation: mastersSkills: ["Problem-solving","Proactive thinking","Communication"]Develop high-performance deep learning solutions for customer frameworks by optimizing model and use-case performance, debugging accuracy and memory issues, and designing model deployment architectures. Implement and extend features in vLLM/SGLang (including inference acceleration approaches) and develop/debug high-performance kernels for Intel accelerators. Collaborate closely with teammates, collaborators, and architects to propose solutions, share status, and improve products.
Loading
Loading job details...
Preparing the role view and application actions.

