The Platform Architecture is looking for a Neural Engine HW Modeling Architect who will work on performance model, compiler and/or C model of the next-generation Neural Engine HW architecture.
Excellent programming skill C++/C and Python is required.Experience in HW performance modeling is a big plus.Knowledge/experience in HW architecture (CPU, GPU, computer architecture in general) and verification is a big plus.Experience in compiler is a big plus. Knowledge in machine learning algorithms (CNN/LSTM etc) and computer vision is a plus.Knowledge in camera pipeline and image processing is a plus.Strong communication skills and ability to work across various groups.
As a modeling architect, you'll work with other HW architects in modeling the performance of the next-generation Neural Engine and/or prototyping a compiler for the given architecture. Solid understanding of modern computer architecture ideas and their HW implementations is required. The tasks involved require cross-functional collaboration with HW design/verification, compiler/FW/driver and ML research teams, and clear verbal and written communication skills are essential.
PhD in CS/EE specializing Machine Learning, Deep Learning or Computer Vision areas. Master degree with industry experience can be considered.