Heterogeneous Computing Expert

1.     Heterogeneous Computing Expert

Work location: Shenzhen

Responsibilities

• Responsible for cooperating with deep learning algorithm engineers to realize the software and hardware joint optimization and acceleration of computer vision/speech semantics and other deep learning algorithms on computing platforms such as CPU, GPU, DSP, and specific embedded reasoning chips;

• Complete the architecture optimization plan of the image algorithm and machine learning algorithm on the embedded device side, and be responsible for the final result of the algorithm optimization on the product side;

• Design and implement algorithms with high-performance basic components on end-side-cloud computing platforms, as well as a cross-platform scheduling framework, to achieve one-click deployment of algorithm models to specific computing platforms;

Requirements:

• Solid computer foundation, familiar with computer architecture and basic technology of parallel computing;

• More than 5 years of C/C++ development experience, proficient in at least one heterogeneous programming language, including but not limited to CUDA, OpenCL, OpenGL and other heterogeneous programming;

•  Familiar with common deep learning models and algorithms, with x86CPU, ARM CPU, GPU, DSP and other embedded reasoning chips and other platform algorithm tuning experience;

• Computer vision and image processing algorithm transplantation experience in various hardware devices is preferred, and experience in the development of TVM, glow, LLVM and other compilers is preferred;

• Have a strong interest in high-performance computing, heterogeneous computing and performance optimization.