About

Amruth Sandhupatla is a skilled Senior Software Engineer II with over seven years of experience in the field. He has a strong background in coding with C/C++, as well as expertise in accelerating Deep Learning models such as Convolutional Neural Networks on GPUs. Amruth's past experience includes working as an R&D Compiler Engineer at Huawei, where he developed optimization passes to optimize OpenGL, GLES, Vulkan, and SPIR-V codes. He was also responsible for making Huawei's testing tools more user-friendly, which benefited employees across Canada and China. His outstanding contributions earned him the Elite and Model awards. As a Graduate Research Assistant at the University of British Columbia, Amruth studied the behavior of neurons in deep convolutional neural networks during training. He designed an innovative algorithm to speed up the training process by skipping neuron computations, resulting in a significant speedup on CPUs and GPUs. His work is currently under review in NIPS 2018. Amruth's education includes a Master's Degree in Computer Engineering from the University of British Columbia and a Bachelor's Degree in Electronics and Communication Engineering from the National Institute of Technology Warangal. In addition to his technical skills, Amruth is a proactive team player who is always looking for ways to improve processes and achieve company targets. His tech stack includes Software Engineering, Deep Learning, Neural Networks, C, test, Research Scientist, and Pytorch.