About the job
As a Qualcomm Machine Learning Engineer, you will develop and implement cutting-edge machine learning techniques that enable the efficient utilization of state-of-the-art solutions across various technology verticals. In this position you will be responsible for contributing to the software design and development of the Qualcomm AI Runtime (QAIRT) delegate for both the ExecuTorch, ONNX Runtime and LiteRT frameworks enabling efficient AI inference on edge devices. You will have the opportunity to show your passion for software design and development with your analytical, design, programming, and debugging skills. You will participate in the agentic transformation of Qualcomm’s development and tooling workflow.
Responsibilities
Design and develop the graph compilation stack that lowers the ExecuTorch Edge IR, ONNX and LiteRT graphs to QAIRT APIs.
Collaborate with cross-functional teams in the AI Software team at Qualcomm to gain knowledge of the capabilities of QAIRT SDK and use it to optimize inference of AI models on Qualcomm AI accelerator IP.
Validate and optimize the performance and accuracy of software through detailed analysis and testing of machine learning use cases.
Debug complex issues, perform root cause analysis, and ensure high system reliability.
Participate in the team's adoption of agentic AI workflows — leveraging tools such as Claude Code, or similar frameworks — to help automate testing, benchmarking, and development activities.
Participate in design and code reviews.
Qualifications
Minimum
Bachelor's degree in Computer Science, Engineering, Information Systems, or related field.
2+ years software development experience using C/C++/Python
Strong software development skills (e.g. data structure and algorithm design, object oriented or other software design paradigm knowledge, software debugging and testing, etc.)
Strong communication skills (verbal, presentation, written)
Foundational knowledge of Machine Learning and Deep Learning
Experience working with one of the Deep Learning frameworks like TensorFlow, PyTorch, ONNX, JAX
Preferred
1+ years Python programming experience
Experience with different NN architectures: DNNs, CNNs, RNNs/LSTMs, GANs, LLMs, etc.
Experience with Graph Compilation technologies, like MLIR, a plus
Familiarity with ExecuTorch, TorchAO, and other related technologies in the PyTorch ecosystem
Familiarity with TfLite, LiteRT, TF, and other related technologies in the TF ecosystem
Familiarity with GenAI model architectures – LLM, LVM, LMM
Experience with optimizing software, specifically AI graph workloads, for embedded platforms
Interest in or exposure to agentic AI frameworks (e.g. Claude Code) and their application to development or testing automation
Ability to collaborate across a globally diverse team and multiple interests