Qualcomm Canada ULC is advancing on-device AI by developing ML/AI compilers for productive mapping of workloads on Qualcomm hardware. You will contribute to compiler development, optimize performance and power, and study ML workloads to inform future HW/SW features, with a focus on PyTorch integration and cross-functional collaboration.
The role requires a robust background in algorithms, performance analysis, and programming in C++/Python, with experience in ML frameworks and compiler flows.