AI SDK Software Engineer
Core
Develop neural network operator kernels and optimize deep learning inference engines for Qualcomm's automotive infotainment and ADAS platforms using Snapdragon chipsets.
Role type
Senior IC AI SDK Software Engineer
Builds
Qualcomm Neural network SDK (QNN/AI Engine Direct SDK) and optimized inference engines for automotive edge devices
Domain
Automotive embedded systems / Deep Learning / Edge AI
Deliverable
production ML models
Required skills
C++, Python, Neural network operator kernel development, Hexagon DSP/SIMD optimization, Quantization-aware training, Post-training quantization, ARM architecture, Model accuracy analysis, Parallel programming (OpenCL, NEON, OpenMP, CUDA)
Preferred skills
PyTorch, ONNX, TensorFlow, TensorRT, QNN, TfLite, NCNN, TNN, MACE, GenAI/LLM deployment, ASR/NLP models, DSP algorithm implementation
Technologies
PyTorch, ONNX, TensorFlow, Hexagon DSP, Snapdragon, OpenCL, NEON, OpenMP, CUDA, QNN, TfLite, NCNN, TNN, MACE, TensorRT
Responsibilities
Develop neural network operator kernels using Hexagon DSP or SIMD accelerator, Optimize performance and tune accuracy for models with Qualcomm AI Toolchains, Design and implement algorithms for standard and user-defined operators, Practice quantization-aware training and post-training quantization, Collaborate with regional teams on new feature design, Support testing teams to improve AI Toolchain quality
Seniority
Senior, hands-on IC
