Senior / Engineer – AI Model Enablement & Software Tools

Snapdragon

Originally posted October 19, 2026 by the employer.

About the role

As an Engineer / Senior Engineer in the Qualcomm AI Stack SDK Software team, you will contribute to bringing modern AI models to Snapdragon platforms using Qualcomm’s AI software stack and model-enablement frameworks. You will analyze, adapt, optimize, quantize, compile, and validate models including Large Language Models, vision models, Vision-Language Models, and multimodal models across Qualcomm AI accelerators.

What you'll do

• Study computational graphs to understand inputs, outputs, operators, tensor shapes, and data flow, and implement model re-authoring, operator decomposition, and graph transformations.
• Convert, optimize, and export models from PyTorch and ONNX for compilation and execution on Qualcomm AI accelerators.
• Apply and validate quantization and calibration flows, including weight and activation quantization, mixed precision, post-training quantization (PTQ), and accuracy-recovery techniques.
• Address Generative AI inference concepts such as transformer attention, KV cache, prefill and decode execution, LoRA, MoE, and speculative decoding.
• Measure and optimize model accuracy, latency, throughput, memory consumption, model size, and power efficiency across software and hardware layers.
• Develop unit, integration, accuracy, performance, and on-device validation tests, authoring maintainable Python and C/C++ code.

What you'll need

• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or related field with 2+ years of experience in software design, development, and delivery (or a Master's degree with 1+ years, or a PhD).
• Programming proficiency in Python and/or C/C++.
• Understanding of software engineering fundamentals including data structures, algorithms, object-oriented design, debugging, testing, and source control.
• Foundational knowledge of AI/ML concepts including neural networks, deep learning, model inference, and model execution workflows.
• Practical experience utilizing agentic coding tools (such as Claude Code, OpenAI Codex, or equivalents) for code exploration, implementation, testing, and debugging, with the ability to review and validate generated code.

Nice to have

• Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• Experience with PyTorch, ONNX, Hugging Face Transformers, or graph-based model representations and tooling such as TorchScript, MLIR, ONNX Runtime, ExecuTorch, or TFLite/LiteRT.
• Understanding of quantization methods including PTQ, QAT, weight and activation quantization, and mixed precision.
• Experience with transformer-based models, LLMs, vision models, or multimodal models, including attention, normalization, feed-forward layers, positional encoding, and KV cache.
• Software development experience in Linux, Android, or RTOS environments (such as QNX), alongside CMake-based builds and Git source control.
• Exposure to Snapdragon SoCs, NPUs, HTPs, or related AI accelerator architectures.

Skills: PyTorch, ONNX, quantization, model enablement, Snapdragon, compiler

More semiconductor jobs: Qualcomm jobs · San Diego jobs