npu-programming jobs in San Diego

Design and architect AI/ML platforms optimized for Qualcomm's hardware (GPU/NPU) and software stack, with focus on end-to-end performance analysis, algorithm tuning, and system bottleneck reduction. Analyze ML workloads across Computer Vision, Audio, Generative AI, and Agentic AI domains; correlate device performance against pre-silicon predictions; and develop reference implementations and tools for third-party developers.…See more Requires 15+ years in high-performance computing systems engineering or software with 5+ years in AI system optimization, strong expertise in AI frameworks and performance profiling, and ability to lead cross-functional teams and articulate complex technical concepts.

Principal-level AI/ML Platform Architect responsible for designing and optimizing AI/ML systems across Qualcomm's hardware and software stacks, particularly for Windows PC/Laptop platforms. The role requires deep expertise in performance optimization, bottleneck analysis, and end-to-end system characterization across GPUs, NPUs, and multiple AI domains (computer vision, audio, generative AI, agentic AI).…See more Candidates must demonstrate 15+ years in high-performance computing systems engineering with 5+ years specifically in AI system optimization, and will interface with cross-functional teams to deliver reference implementations, tools, and documentation for third-party developers.

Lead the design and development of embedded NPU software frameworks, runtime libraries, and system drivers for Qualcomm's Snapdragon SoC portfolio, optimizing for high-performance AI and multimedia workloads across mobile, automotive, compute, and XR platforms. Architect solutions across the full stack from low-level drivers to high-level frameworks, collaborating with hardware and systems teams to deliver production-grade solutions.…See more Drive technical decisions, mentor engineers, and optimize software using advanced NPU architecture techniques including SIMD, multi-threading, and memory hierarchy optimization. Requires deep expertise in embedded systems, C/C++, NPU architecture, real-time operating systems, and demonstrated ability to lead complex development efforts across cross-functional teams.

Lead the design and development of embedded NPU software frameworks, runtime libraries, and system drivers for AI acceleration across Snapdragon SoCs. Architect optimizations for high-performance, low-power multimedia and machine learning workloads spanning mobile, automotive, compute, and XR platforms.…See more Work across the full software stack—from low-level drivers to high-level frameworks—collaborating with hardware and systems teams. Mentor engineers, drive technical decisions, and own system-level integration across CPU/DSP/NPU subsystems.