GPU/异构计算硬件选型与应用工程师-Data（北京）
Core
Formulating selection roadmaps, evaluating, introducing, and delivering GPU/heterogeneous computing (FPGA/ASIC) components; adapting and tuning GPU/heterogeneous computing models for machine learning/AI business; evaluating and tuning performance and stability of GPU/heterogeneous computing servers; monitoring, diagnosing, and handling GPU/heterogeneous computing faults in data centers; collaborating with industry alliances and open standard committees on emerging technology research and new standard customization.
Role type
Senior IC GPU/heterogeneous computing hardware selection and application engineer
Builds
GPU/heterogeneous computing components, servers, and optimized AI/ML platforms
Domain
Hardware engineering + AI/ML infrastructure
Deliverable
production ML models
Required skills
GPU/AI platform architecture design, application performance optimization, system evaluation, performance analysis, performance tuning, system architecture (GPU/AI SoC/platform interconnect/memory subsystem/GPU Direct RDMA), GPU/AI virtualization, deep learning architecture, distributed systems
Preferred skills
Expertise in GPU/AI SoC or platform architecture, interconnect structures, memory subsystems, GPU Direct RDMA; expertise in GPU/AI virtualization, deep learning architecture, or distributed systems
Technologies
FPGA, ASIC, GPU Direct RDMA, deep learning frameworks, distributed systems
Responsibilities
Develop and execute GPU/heterogeneous computing component selection roadmaps; Adapt and tune GPU/heterogeneous computing models for ML/AI workloads; Evaluate and optimize server performance and stability; Monitor, diagnose, and resolve GPU/heterogeneous computing faults in data centers; Collaborate on emerging technology research and standard customization
Seniority
Senior, hands-on IC