Responsibilities
1. Formulation, evaluation, introduction and delivery of roadmap plans for GPU/heterogeneous computing (FPGA/ASIC) component selection 2. Responsible for the adaptation and performance optimization of GPU/heterogeneous computing models for machine learning/AI and other businesses 3. Responsible for performance evaluation and stability tuning of GPU/heterogeneous computing servers, analyzing and optimizing system performance bottlenecks 4. Follow up on 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 technologies and methods of GPU/AI platform system evaluation, performance analysis, and performance tuning 4. Knowledge of computer system architecture, especially GPU/AI Applicants with expertise in one of SoC or platform architecture, interconnect structure, memory subsystem, and GPU Direct RDMA will be given priority 5. Applicants with expertise in one of business applications such as GPU/AI virtualization technology, deep learning architecture, and distributed systems will be given priority.
