Principal SW Engineer - LLM Serving (Cloud AI)
San DiegoLast seen 7 days ago
Summary
Principal Software Engineer role on Qualcomm's Cloud AI team focused on LLM serving and inference acceleration. The engineer will design, optimize, and deploy high-performance software across the product lifecycle, from R&D through commercial deployment, with expertise in serving frameworks (vLLM), PyTorch, neural network optimization, and multi-core/SoC architecture performance modeling. Strong C++/Python development skills, deep LLM/multi-modal model understanding, and experience with machine learning accelerators are required; experience with compiler technology, performance analysis, and commercial software delivery at scale is essential.