5 days ago
Markham, CanadaStaff+
Responsibilities
- Own and deliver key aspects of the Qualcomm AI software stack.
- Develop optimization algorithms for machine-learning operators and layers.
- Enhance AI software frameworks for optimal neural-network resource usage on Qualcomm hardware.
- Develop profiling and debugging tools to accelerate deployment of new neural networks.
- Evaluate and optimize neural-network runtime performance and accuracy.
- Work with customer teams to enable network models and AI software features for customer use cases.
- Coordinate development across software, hardware, architecture, and customer teams.
- Contribute to commercial-quality software releases and software quality process improvements.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field plus 4+ years of relevant engineering experience; or a master’s degree plus 3+ years; or a PhD plus 2+ years.
- Ideal candidates have 5+ years of industry experience.
- Strong software development, programming, analytical, development, and debugging skills.
- Experience with C/C++ and Python, including C++ work experience.
- Preferred experience with Android or embedded Linux software development.
- Experience optimizing algorithms for hardware acceleration cores using OpenCL, OpenGL ES, and/or DSPs.
- Experience with NumPy and deep-learning frameworks such as TensorFlow and PyTorch.
- Background in linear algebra, fast math libraries, multithreading, and vector instruction sets.
- Strong verbal, presentation, written communication, collaboration, and continuous-learning skills.
Categories
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.