Build machine learning compilers at Qualcomm Canada ULC using C++ and Python to optimize on-device AI performance and power. Work across sites and functions.
As a Staff Machine Learning Framework and Performance Engineer, you will develop production and exploratory ML/AI compilers. You will define algorithms mapping workloads onto Qualcomm hardware, couple Py Torch with compiler flows, and analyze network design trends. The work supports future Qualcomm ML hardware and software offerings through performance analysis and simulation.
Key Responsibilities: Develop and evolve ML/AI compilers within Qualcomm
Implement algorithms for high-performance, low-power Qualcomm hardware
Connect Py Torch frameworks with Qualcomm compiler flows
Analyze performance, area,
and power trade-offs
Simulate future So C hardware and software algorithms
Requirements: Bachelor's degree and four-plus years of related experience
Master's degree and three-plus years of related experience
Ph D and two-plus years of related experience
Strong algorithm development and performance analysis background
Solid C++ and Python knowledge is an asset
Apply compiler development, algorithm expertise, and performance analysis to Qualcomm’s evolving ML and AI hardware systems.