Develop and implement strategies to optimize AI model inference for on-device deployment. Employ techniques like pruning, quantization, and knowledge distillation to minimize model size and computational demands. Optimize performance-critical components...
Develop features and tools as part of solution engineering efforts to support all Enterprise Service offerings including, but not limited toDPU/NIC/networking/switchingproducts. Work with NVIDIA Enterprise customers and internal users to...
Work on developing the new PHY layer for the 800G and higher InfiniBand and Ethernet Switch and NIC (network adapter) product lines. Be responsible for design, developing, and delivering new...
Own the responsibility for delivering Networking features and their verification aspects. Define, develop and maintain verification infrastructure and regression tests suites - make test suites robust, maintainable and easy portable....
Support the integration of our latest Ethernet technology with major cloud providers in China. Assist with the deployment of new supercomputer technologies and data centers. Build and maintain customer trust...
Develop and implement strategies to optimize AI model inference for on-device deployment. Employ techniques like pruning, quantization, and knowledge distillation to minimize model size and computational demands. Optimize performance-critical components...