Machine Learning Engineer, Frameworks & Performance (New Grad to Principal level)
Core
Developing and evolving ML/AI compilers for efficient mapping of algorithms on Qualcomm hardware, and analyzing workloads to drive future HW/SW features.
Role type
Senior IC machine learning systems engineer (compiler & performance)
Builds
ML/AI compilers and performance simulation components for Qualcomm SoCs
Domain
Semiconductor hardware engineering and machine learning systems
Deliverable
production ML models
Required skills
C++, Python, algorithm development, performance analysis, compiler design, computer architecture, data structures
Preferred skills
PyTorch, ONNX, CPU/DSP/GPU design, simulation tools (C++, Python), on-silicon debugging
Technologies
PyTorch, ONNX, C++, Python, Git, Jenkins, Docker, clang, MSVC
Responsibilities
Develop ML/AI compilers for efficient algorithm mapping; Define algorithms for compiling ML workloads for high performance/low power; Create performance-driven simulation components; Run and analyze performance simulations to suggest HW/SW enhancements; Pre-silicon performance prediction for ML algorithms.
Seniority
Senior, hands-on IC
