AI服务器系统集成测试-服务器
Core
End-to-end delivery testing for GPU cards and servers, including selection validation, R&D verification, SIT, production testing, and acceptance, ensuring project delivery and quality standards.
Role type
Senior IC GPU server system integration test engineer
Builds
GPU server products for AI workloads
Domain
Hardware testing / AI infrastructure
Deliverable
production ML models
Required skills
GPU hardware architecture knowledge, server hardware testing, performance benchmarking, Python automation development, test framework design, cross-functional collaboration
Preferred skills
CUDA kernel optimization, post-silicon validation, large-scale AI cluster networking (IB/RoCE), CI/CD pipeline construction
Technologies
Python, Shell, CUDA, PCIe, NUMA, IB, RoCE
Responsibilities
Execute end-to-end testing for GPU cards and servers from selection to delivery; Build and maintain GPU SIT baseline systems covering functionality, performance, and stability; Evaluate and benchmark new GPU cards to support product selection; Optimize SIT standards based on business scenarios to improve stability; Develop automated testing frameworks and pipelines for efficiency.
Seniority
Senior, hands-on IC