New Graduate- AI SW SDK Engineer

Neural network operator development, with Hexagon DSP or SIMD accelerator. Performance and accuracy tuning and optimizations with QC AI Engine Direct SDK. Algorithms prototype design and implementation for user defined operators. Practices on quantization aware training and post-training quantization. Co-work with our global team on new feature design and implementation. Support testing team to improve the quality of our products. Support customer to deploy their neural networks with highest performance and accuracy. Bachelor's degree in Engineering, Information Systems, Computer Science, or related field. 2-3 years C/C++ programming experience on Linux or other embedded system. Ability to collaborate across a globally diverse team, have a good sense of responsibility and teamwork. Have the concept of SDK development for variant system platforms. Familiar with ARM architecture. Familiar with popular quantization framework is a plus: ONNX QDQ, Pytorch, TensorFlow, PPQ, TensorRT. Enthusiasm in machine learning technology. Hand-on experience in design/implementation of deep learning networks via modern frameworks. Excellent software design, problem solving, debugging, documentation and presentation skills and proved experiences. Development on deep learning inference framework relevant practical experience is a plus, such as QNN, TfLite, NCNN, TNN, MACE, etc. Familiar with fixed-point quantitative algorithms and implementation. Familiar with popular deep learning frameworks: TensorFlow, Pytorch, ONNX, etc. Familiar with parallel programing, such as OpenCL, NEON, OpenMP, Cuda, etc. DSP software development and algorithm implementation, familiar with Hexagon/HVX is a big plus. Having quantization experience on TensorFlow or Pytorch is a plus. Experienced with LLM/LVM or ASR/NLP related models is a plus.