平头哥-AI chip performance/power architect-上海

Collaborate with the software and hardware team to design and optimize general purpose AI chip architectures. Conduct in-depth performance and power analysis of AI chip workloads. Identify and address performance bottlenecks and power issues in the architecture. Collaborate with the software and hardware teams to optimize AI chip performance and improve power efficiency through micro-architectural and algorithmic improvements. Stay up-to-date with the latest advancements in AI chip technology and performance/power optimization techniques. Conduct research and experiments to explore new performance/power optimization opportunities.

Deep understanding of general purpose AI chip architecture; Experience with performance profiling and analysis tools (e.g., NVIDIA Nsight). Familiarity with AI chip programming models (especially for CUDA). Experience with RTL design and power analysis tools (e.g., PTPX). Strong analytical and problem-solving skills. Excellent communication and collaboration skills. Familiarity with AI workloads is a plus.