Software Engineer, LiteRT / On-Device AI
Core
Develop and optimize the software stack for running AI and LLM models on Qualcomm's NPU, including the LiteRT runtime and QNN SDK.
Role type
Senior IC machine-learning engineer (on-device inference)
Builds
LiteRT (Google's on-device ML inference runtime), LiteRT-LM (LLM layer), and QNN SDK
Domain
Semiconductor / Edge AI / Machine Learning
Deliverable
production ML models
Required skills
C++, Python, computer architecture, operating systems, NPU/DSP/GPU programming, model optimization, embedded systems, low-level programming, version control
Preferred skills
LLM/generative model architecture, quantization, ML frameworks (TensorFlow, PyTorch, LiteRT), performance tuning for edge devices
