Responsibilities
1. Formulate, evaluate, introduce and deliver the selection roadmap plan for GPU/heterogeneous computing (FPGA/ASIC) components 2. Be responsible for the adaptation and performance tuning of GPU/heterogeneous computer models for machine learning/AI and other businesses 3. Be responsible for the performance evaluation and stability tuning of GPU/heterogeneous computing servers, and analyze and optimize system performance bottlenecks 4. Follow up the monitoring, diagnosis and processing of GPU/heterogeneous computing failures in the data center 5. Cooperate with industry alliances and open standards committees to participate in emerging technology research and the customization of new standards.
Qualifications
1. Master degree or above in electrical engineering, computer engineering, computer science or related majors 2. More than 5 years of experience in GPU/AI platform architecture and/or application performance optimization design or platform evaluation 3. Familiar with the techniques and methods of GPU/AI platform system evaluation, performance analysis, and performance tuning 4. Those who have expertise in computer system architecture, especially GPU/AI SoC or platform architecture, interconnect structure, memory subsystem, GPU Direct RDMA, will be given priority 5. Those who have expertise in GPU/AI virtualization technology, deep learning architecture, distributed systems and other business applications will be given priority.
