As a Machine Learning Engineer at Qualcomm Technologies, Inc., you will join the AI Software team to design and develop the graph compilation stack for the Qualcomm AI Runtime (QAIRT) delegate across ExecuTorch, ONNX Runtime, and LiteRT frameworks, enabling efficient AI inference on edge devices. Your daily tasks include collaborating with cross-functional teams to optimize AI model performance using QAIRT SDK, validating software through detailed analysis and testing of machine learning use cases, and participating in the adoption of agentic AI workflows for automation. The role requires proficiency in C/C++/Python, experience with deep learning frameworks like TensorFlow or PyTorch, and familiarity with graph compilation technologies such as MLIR. Knowledge of GenAI model architectures and embedded platform optimization is a plus, making this an ideal position for those passionate about advancing the state-of-the-art in AI software development at scale.