Machine Learning Engineer Role Overview
In this position, you will be responsible for designing and implementing advanced machine learning solutions to improve the efficiency and accuracy of our compiler.
You will work closely with cross-functional teams to integrate cutting-edge technologies into our platforms.
This is an exciting opportunity to shape the future of energy-efficient machine learning technology and contribute to impactful advancements in the field.
Key Responsibilities:
* Design and implement machine learning compilers using PyTorch and C++ tailored for our Neural Processing Unit (NPU) architecture.
* Develop and enhance ML models to improve model efficiency and accuracy.
* Collaborate with architecture and software engineering teams to integrate cutting-edge ML technologies into our platforms.
* Research and prototype innovative solutions in ML compiler design and system-level optimizations.
* Optimize ML workloads for deployment across diverse devices.
Qualifications:
* Bachelor's or advanced degree in Computer Science, Electrical Engineering, Machine Learning, or a related discipline.
* Strong expertise in PyTorch and C++ programming.
* Experience with ML workload analysis, compiler development, and quantization techniques.
* Familiarity with deep learning frameworks such as TensorFlow or ONNX is a plus.
Preferred Qualifications:
* Experience with ML model deployment on hardware accelerators such as GPUs, TPUs, or NPUs.
* Understanding of system-level architecture and low-level programming.
Why Join Our Team?
At Qualcomm, you'll be part of an innovative team that drives impactful advancements in machine learning technology. As a member of the NPU Architecture team, you'll work directly with strategic customers to create customized solutions while shaping the future of energy-efficient machine learning. Your contributions will support technology that powers more devices worldwide than any other machine learning solution.