LLM Serving Engineer

Summary

As an LLM Serving Engineer at Qualcomm, you will design and optimize machine learning frameworks, runtime systems, and inference software to deploy AI models efficiently on hardware. You'll work on hardware-software co-design for ML solutions across mobile, edge, automotive, and IoT platforms, developing compiler tools, model efficiency software, and optimized ML kernels. The role requires 6+ years of systems/software engineering experience with demonstrated expertise in ML frameworks (TensorFlow, PyTorch, Keras), low-level OS-hardware interactions, embedded systems optimization, and programming in Python or C++. You'll lead technical initiatives, mentor team members, and collaborate with cross-functional teams on complex product-level ML features.