AI Server Head
AI Server Head
CyberTAN Technology- Posted 5 hours ago
- Be among the first 10 applicants
Job Description
< Be Welcome>
- Competitive Salary and Benefits offering
- Location in Taipei or Hsinchu
- Responsible for Team building development, architect defining, and foster a collaborative.
- Responsible for leading AI Server multidisciplinary engineering teams to deliver AI server platforms—including GPUs, high-speed networking, and liquid cooling technologies—balancing performance, cost, and manufacturability.
- Responsible for leading end-to-end development and delivery of AI server systems based on AMD GPU and CPU technologies
- Responsible for Cross-Functional Execution Hardware (server / board / power)、Firmware (BIOS / BMC)、Validation (SI/PI, stress, reliability)、Manufacturing & supply chain; and ensure readiness across.
- Responsible for developing talent team, to mentor team to align goals and enhance managerial effectiveness.
- Responsible for risk management identify and mitigate risks and lead cross-team issue resolution and escalation.
- Responsible for maintain deepen relationships with key accounts customers and strategic collaborations.
- AI software stack enablement
- 團隊熟悉 ROCm,確保 PyTorch / TensorFlow 在 AMD 平台穩定運行並達到最佳效能。
- Distributed training performance optimization
- 具備優化大規模訓練效能能力,包含 RDMA / RoCE 與 DCQCN 等網路調校。
- HW/SW co-design & system debug
- 主導軟硬體協同設計與問題分析,快速定位並解決系統層級效能與穩定性問題。
More Info
Key Skills
RDMA
AMD GPU and CPU technologies
DCQCN
HW SW co-design
RoCE
Distributed training performance optimization
system debug
ROCm
