AI Kernel Engineer Intern - Kernel Optimization
Core
Implement and optimize ONNX operator kernels for a general-purpose neural processing unit (GPNPU) to accelerate neural network inference on edge and endpoint devices.
Role type
AI Kernel Engineer Intern
Builds
ONNX operator kernels for Quadric GPNPU
Domain
Edge computing / Semiconductor hardware / Neural network inference
Deliverable
production ML models
Required skills
C/C++/Python, kernel implementation, kernel optimization, performance profiling
Preferred skills
MS in CS/CE or related fields
Technologies
ONNX, C++, Python
Responsibilities
Implement ONNX operator kernels not yet in SDK; optimize kernel performance using profiling tools.
Seniority
Intern
Sourced via workable · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
