4 days ago
Markham, CanadaEntry Level
Responsibilities
- Develop and evolve Qualcomm’s production and exploratory ML/AI compilers.
- Define and implement algorithms that compile ML/AI workloads for high performance and low power on Qualcomm hardware.
- Integrate PyTorch efficiently with Qualcomm ML/AI compiler flows.
- Analyze ML network trends, workloads, and performance, area, and power trade-offs to guide future hardware and software design.
- Create C++ and Python performance-driven simulation components for future SoCs and perform pre-silicon performance prediction.
- Run, debug, and analyze performance simulations to identify framework, compute, and system-memory bottlenecks.
- Collaborate across sites and functions with engineering teams, customers, and academic research communities.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field plus 8+ years of related experience; or a master’s degree plus 7+ years; or a PhD plus 6+ years.
- Strong background in algorithm development and performance analysis.
- Strong problem-solving, analytical, debugging, communication, learning, and adaptability skills.
- Strong object-oriented design principles and knowledge of C++ and Python are significant assets.
- Experience with compiler, CPU, DSP, or GPU design and development is an asset.
- Knowledge of PyTorch, ONNX, algorithms and data structures, computer architecture, digital circuits, and event-driven transactional models or simulators is valuable.
- Familiarity with revision control, CI/CD, Git, Jenkins, Docker, Clang, or MSVC is valuable.
- On-silicon debugging experience with high-performance compute algorithms is valuable.
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.