GenAI Software Engineer
Core
Design and develop end-to-end AI tools, models, and software to enable efficient deployment of quantized neural networks on Qualcomm hardware, focusing on optimizing performance for speed, latency, memory, and power consumption.
Role type
Senior IC GenAI Software Engineer (LLM optimization & on-device deployment)
Builds
Quantized neural network models and deployment toolchains for Qualcomm CPU/NPU/GPU
Domain
Mobile AI / Edge Computing / LLM Inference
Deliverable
production ML models
Required skills
Python, C/C++, LLM computation graph optimization, LLM inference engine optimization, operator/kernel-level optimization, deep learning frameworks (PyTorch, vLLM, SGLang), CI/CD pipelines, debugging and profiling
Preferred skills
Qualcomm QNN SDK, Android programming, AI coding assistants (Claude, Codex, Cursor), Agentic AI pipeline experience
Technologies
QNN SDK, vLLM, SGLang, llama.cpp, PyTorch, Hugging Face, CI/CD tools
Responsibilities
Design and develop end-to-end AI tools and software for quantized neural network deployment; Deploy AI models to Qualcomm CPU/NPU/GPU; Develop debugging and profiling tools; Build and maintain automated test suites; Collaborate with cross-functional teams to design development/test approaches; Analyze test results and provide actionable feedback
Seniority
Senior, hands-on IC
