AI SDK Software Engineer

Company:

Qualcomm China

Job Area:

General Summary:

Job overview:

As a member of Qualcomm China's engineering team dedicated to automotive infotainment and ADAS platforms, you will play a pivotal role in advancing embedded deep learning solutions. We are seeking skilled engineers with expertise in machine learning to drive innovation and development in this dynamic domain.

Our objective is to seamlessly integrate high-performance software with advanced hardware, enabling rapid execution of deep neural networks. This approach is designed to optimize and enrich the driving experience-particularly in ADAS and GenAI applications-by leveraging the full potential of Snapdragon chipsets embedded within modern vehicles.

In this position, you will work extensively with neural network frameworks such as PyTorch and ONNX, contributing to the continuous enhancement of our neural network inference engine to support cutting-edge deep learning models emerging from both academia and industry. You will also be responsible for optimizing and fine-tuning these applications for Qualcomm’s next-generation hardware acceleration platforms, including DSP, GPU, and CPU, ensuring maximum performance and efficiency.

The work scope includes but not limit to:

Feature development and bug fix in Qualcomm Neural network SDK (QNN/AI Engine Direct SDK). Develop neural network operator kernels using Hexagon DSP or SIMD accelerator. Optimize performance and tune accuracy for models with Qualcomm AI Toolchains. Algorithms prototype design and implementation for standard and user-defined operators. Practice quantization-aware training and post-training quantization. Collaborate with different regional teams on new feature design and implementation. Support the testing team to improve the quality of AI Toolchains. Assist customers in efficiently deploying their neural networks.

Minimum Qualifications:

5-6 years of software development experience with the ability to independently complete projects on edge platforms. Proficiency in at least one programming language (e.g., C++, Python). Strong problem-solving and logical thinking skills. Excellent communication skills, capable of effective collaboration with cross-functional teams. Experience with agile development methodologies is a plus. Have the concept of SDK development for variant system platforms. Familiar with ARM architecture-based hardware and software.

Preferred Qualifications:

Enthusiasm for machine learning technology and hands-on experience in designing and implementing deep learning networks using modern frameworks. Familiarity with popular quantization frameworks such as ONNX QDQ, PyTorch, TensorFlow, PPQ, TensorRT. Experience with model accuracy analysis, problem-solving, and debugging. Proven experience in software design, problem-solving, debugging, documentation, and presentation. Practical experience with deep learning inference frameworks such as QNN, TfLite, NCNN, TNN, MACE. Familiarity with popular deep learning frameworks like PyTorch, ONNX, TensorFlow. Experience with parallel programming, such as OpenCL, NEON, OpenMP, CUDA. DSP software development and algorithm implementation experience, familiarity with Hexagon/HVX is a big plus. Experience in quantization tuning for GenAI models on edge and related inference acceleration is a strong plus. Experience with ADAS/VLA, GenAI/LLM/LVM, or ASR/NLP related models' deployment is a plus.

Minimum Qualifications:

OR

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

OR

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.

Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail [email protected] or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).

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.

To all Staffing and Recruiting Agencies:Our Careers Site is only for individuals seeking a job at Qualcomm. Staffing and recruiting agencies and individuals being represented by an agency are not authorized to use this site or to submit profiles, applications or resumes, and any such submissions will be considered unsolicited. Qualcomm does not accept unsolicited resumes or applications from agencies. Please do not forward resumes to our jobs alias, Qualcomm employees or any other company location. Qualcomm is not responsible for any fees related to unsolicited resumes/applications.

If you would like more information about this role, please contact Qualcomm Careers.