Software Engineer, AI Software Tools (Multiple Levels)

Qualcomm•San Diego, CA

56d

About The Position

General Summary As a leading technology innovator, Qualcomm pushes the boundaries of what's possible to enable next-generation experiences and drive digital transformation, creating a smarter, connected future for all. As an AI Software Tools Software Engineer, you will develop, implement, and optimize cutting-edge machine learning techniques, frameworks, and tools that enable the efficient utilization of state-of-the-art solutions across a broad set of technology verticals and designs. In this role, you will be responsible for designing, developing, and optimizing features for the Qualcomm AI Stack, SDKs, and associated tools, including delegate support for ONNX Runtime, Executorch, and TFLite/LiteRT frameworks. You will target the optimization and acceleration of AI models on Qualcomm Snapdragon platforms and AI accelerators, contributing to the efficient execution of advanced deep neural networks (DNNs), large language models (LLMs), and other modern AI architectures. You will have the opportunity to demonstrate your passion for software design and development through your analytical, design, programming, and debugging skills. Depending on level, you may assist or lead feature development, research and recommend leading technologies, and provide guidance to junior team members. You will collaborate with cross-functional teams to deliver robust, scalable AI software solutions, and contribute to a culture of technical excellence, knowledge sharing, and continuous improvement within the AI Software team.

Requirements

Bachelor's degree in Engineering, Information Systems, Computer Science, or related field.
2+ years (Senior) / 5+ years (Staff) of software development experience with Python and C/C++.
Strong software development skills (e.g., data structure and algorithm design, object-oriented or other software design paradigms, software debugging and testing).
Experience in using and developing AI solutions in one or more of these frameworks: Tensorflow, JAX, TFLite, LiteRT, PyTorch, ExecuTorch, ONNX Runtime.
Foundational knowledge of Machine Learning and Deep Learning.
Strong communication skills (verbal, presentation, written).

Nice To Haves

Master's degree in Computer Science, Computer Engineering, or Electrical Engineering.
1+ years (Senior) / 2+ years (Staff) building commercial software products.
Experience with Executorch, TorchAO, and other related technologies in the PyTorch ecosystem.
Experience with AI optimization frameworks (e.g., Olive, ONNX optimizer, TVM, Optimum).
Experience with different NN architectures: DNNs, CNNs, RNNs/LSTMs, GANs, LLMs, MoE, LVM, LMM, and other modern AI network architectures.
Experience with different quantization techniques (PTQ, QAT, AWQ, SpinQuant, etc.).
Understanding of linear algebra as used in ML graph processing.
Experience with optimizing software, specifically AI graph workloads, for embedded platforms.
Experience processing different ML graph formats like ONNX, TorchScript, and MLIR.
Experience with low-level interactions between operating systems (Linux, Android, QNX, Windows) and hardware.
Linux software development experience.
Experience using/integrating Qualcomm AI Stack products (e.g., QNN, SNPE, QAIRT).
Experience with agile software development practices and git-based SCM.
Ability to collaborate across a globally diverse team and multiple interests.

Responsibilities

Design, develop, and optimize features for the Qualcomm AI Stack SDKs and tools to support execution of the latest neural networks on Snapdragon platforms.
Design, develop, and optimize features for ONNX Runtime Execution Provider, ExecuTorch Edge IR graph lowering stack, and LiteRT delegates.
Validate, analyze, and optimize the performance and accuracy of software through detailed testing of machine learning use cases.
Debug complex issues, perform root cause analysis, and ensure high system reliability.
Collaborate with cross-functional teams to deliver robust, scalable AI software solutions.
Lead or assist in feature development and application of machine learning techniques into products and AI solutions, enabling customers to do the same.
Research and recommend leading technologies related to the PyTorch and ONNX ecosystems, model architectures, graph lowering and optimization techniques, and quantization methods.
Contribute to a culture of technical excellence, knowledge sharing, and continuous improvement within the AI Software team.
Participate in design and code reviews.
Work independently with minimal supervision; Staff Engineers provide guidance to junior team members and make decisions impacting their area and the broader work group.