NPU Software Operator Engineer

Responsibilities:
● Neural network operator design and development with C/C++/Assembly.
● Operator verification on simulation/emulation platform and real hardware.
● Operator performance benchmarking.
● Operator performance profiling and optimization.
 
Minimum Qualifications:
● CS/EE MS 3+ years relate work experience.
● Strong coding skills in C/C++ and Python.
● Having solid math foundation.
● Experienced in DSP/x86/GPU code performance optimization.
● Familiar with popular framework like Tensorflow, Caffe, Mxnet.
● Familiar with dev/build utility (like git, CMake, Bazel etc.) and shell script(like bash).
● Good communication skill and technical leadership.
 
Preferred Qualifications:
● Familiar with popular CNN, RNN models like Resnet50, Googlenet, VGG16.
● Experience in using HW emulation platform, including Palladium, Zebu, or FPGA.
● Experience in instruction pipeline optimization.
● Experience in DMA performance optimization.
● Experience in CUDA C programing and performance tuning.