3 days ago
Markham, CanadaMid Level
Base Salary
$105k - $155k/yr
Responsibilities
- Develop and evolve production and exploratory ML/AI compilers for efficient mapping of ML/AI algorithms onto current and future Qualcomm hardware.
- Define and implement algorithms that compile ML/AI workloads for high performance and low power.
- Create algorithms that efficiently couple PyTorch with Qualcomm ML/AI compiler flows.
- Analyze ML network-design trends, customer requirements, and academic research to inform software and hardware design.
- Explore performance, area, and power trade-offs for future ML hardware and software algorithms.
- Build C++ and Python performance-driven simulation components for future SoC hardware/software analysis.
- Predict pre-silicon performance for ML algorithms and run, debug, and analyze performance simulations.
- Collaborate across sites and functions to recommend enhancements addressing framework, compute, and system-memory bottlenecks.
Requirements
- Bachelor's degree in Computer Science, Engineering, Information Systems, or a related field.
- Strong background in algorithm development and performance analysis.
- Strong knowledge of C++ and Python, with strong object-oriented design skills.
- Strong problem-solving, analytical, debugging, communication, learning, and adaptability skills.
- Compiler design and development experience is an asset.
- Knowledge of network model formats or platforms such as PyTorch and ONNX is a strong asset.
- Familiarity with Git, Jenkins, Docker, Clang, and MSVC is an asset.
- Knowledge of algorithms and data structures, computer architecture, digital circuits, and event-driven transactional models or simulators is useful.
- On-silicon debugging skills for high-performance compute algorithms are useful.
Benefits
- Annual base pay range of $104,800.00-$154,800.00, plus a competitive annual discretionary bonus program and potential annual RSU grants.
- Competitive benefits package supporting employees at work, at home, and at play.
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.