Qualcomm AI SDK Software Engineer 

China, Shanghai 

430444629

Job Area:

Engineering Group, Engineering Group > Software Engineering

As a leading technology innovator, Qualcomm pushes the boundaries of what's possible to enable next-generation experiences and drives digital transformation to help create a smarter, connected future for all. As a Qualcomm Software Engineer, you will design, develop, create, modify, and validate embedded and cloud edge software, applications, and/or specialized utility programs that launch cutting-edge, world class products that meet and exceed customer needs. Qualcomm Software Engineers collaborate with systems, hardware, architecture, test engineers, and other teams to design system-level software solutions and obtain information on performance requirements and interfaces.

Minimum Qualifications:

• Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 4+ years of Software Engineering or related work experience.

Master's degree in Engineering, Information Systems, Computer Science, or related field and 3+ years of Software Engineering or related work experience.

PhD in Engineering, Information Systems, Computer Science, or related field and 2+ years of Software Engineering or related work experience.

• 2+ years of work experience with Programming Language such as C, C++, Java, Python, etc.

Job overview:

We combine high performance software with cutting edge hardware to run deep neural nets fast, and we enhance your driving experience in the most efficient way possible on that powerful Snapdragon chipset inside vehicle.

You will work with neural network frameworks like Pytorch and TensorFlow, extend our neural net engine to support the latest and SOTA DNNs emerging from the research community and industry, and optimize for Qualcomm next generation hardware acceleration cores (DSP/GPU/NPU/CPU).

The work scope includes but not limit to:

• Development and bug fix in Qualcomm Neural network SDK (QNN/AI Engine Direct SDK)

• Performance optimizations and accuracy tuning with QC AI Engine Direct SDK.

• Practices on quantization aware training and post-training quantization.

• Model quantitative analysis and new algorithms.

• SDK development on Automotive OS platforms (QNX/Android/Hypervisor).

• Neural network operator development, with Hexagon DSP or SIMD accelerator.

• Algorithms prototype design and implementation for user defined operators.

• Co-work with our global team about new feature design and implementation.

• Support our testing team to improve the quality of our products.

• Support our customer to deploy their neural networks with efficient way.

Minimum Qualifications:

• 3+ years C/C++ programming experience on Linux or other embedded system.

• Excellent communication skills (verbal, presentation, written).

• Ability to collaborate across a globally diverse team, have a good sense of responsibility and teamwork.

• Experienced with Python programming.

• Experience in tuning and analysis the quantization accuracy of models.

• Have the concept of SDK development for variant system platforms.

• Familiar with ARM architecture.

Preferred Qualifications:

• Enthusiasm in machine learning technology, and 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 popular quantization framework is a plus: ONNX QDQ, Pytorch, TensorFlow, PPQ, TensorRT.

• 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 model accuracy analysis and problem solving, debugging.

• Familiar with fixed-point quantitative algorithms and implementation.

• Experienced with LLM/LVM or ASR/NLP, and ADAS/BEV related models is a plus.

Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.