Enterprises

This project aims to address the challenges of efficiently executing multiple AI recognition tasks on resource-constrained edge devices. Interns will conduct research on heterogeneous computing architectures and design a dynamic resource scheduling system tailored to the specific characteristics of CPUs, GPUs, and NPUs to achieve multi-objective optimization. This project offers a comprehensive implementation opportunity, ranging from low-level hardware abstraction to high-level algorithm design. It is ideal for students interested in High-Performance Computing (HPC), AI system deployment, and operational optimization.