Qualcomm is seeking an AI Performance Engineer to optimize and deploy machine learning models for inference acceleration on cloud AI hardware. The role involves converting and optimizing language models, vision models, and diffusion models using PyTorch and ONNX, analyzing performance bottlenecks, and designing efficient kernels in Triton. You will collaborate with compiler, firmware, and platform teams to map next-generation AI workloads onto hardware, working across the full product lifecycle from research to commercial deployment. The position requires deep expertise in transformer architectures, inference optimization techniques, computer architecture, ML accelerators, and distributed systems.

As a Staff Software Engineer on Qualcomm's AI Software team, you will lead design and development of core features in the Qualcomm AI Stack (QAIRT and Genie), optimizing deep neural networks and large language models for execution on Snapdragon mobile platforms. You will drive AI runtime framework components for resource-constrained mobile systems, working closely with OEM partners and customer teams to deliver features, optimizations, and bug fixes required for product launches. The role demands expertise in optimizing for power, memory, and performance constraints while maintaining high code quality through design reviews and mentoring junior engineers. You will debug complex system issues across software-hardware boundaries and proactively improve developer workflows, tools, and documentation.