Staff Machine Learning Engineer

Company: Qualcomm China Job Area: Engineering Group, Engineering Group > Software Engineering General Summary:

Artificial Intelligence is changing the world for the benefit of human beings and societies. QUALCOMM, as the world’s leading mobile computing platform provider, is committed to enable the wide deployment of intelligent solutions on all possible devices – like smart phones, laptops, autonomous vehicles, robotics and IoT devices. Qualcomm is creating building blocks for the intelligent edge. In this role you will develop tools to help developers optimize and deploy machine learning models on edge and mobile hardware.  AIMET  is Qualcomm's open-source library for state-of-the-art model quantization, and compression techniques. You will develop and support cutting-edge model optimization workflows — pushing the boundary of what's possible on resource-constrained hardware. Applications range from quantizing large language models (LLMs) and generative AI models to compressing latency-critical vision, audio, and multimodal networks for deployment on Qualcomm Snapdragon and other edge SoCs.  For this role we are seeking a talented and motivated Staff Software Engineer with expertise in the optimizing and deploying ML models – especially for edge devices.

Design, develop, and maintain quantization algorithms and compression pipelines within the AIMET framework (PTQ, QAT, mixed-precision, AdaScale etc.)  Implement advanced quantization techniques including weight-only quantization, activation quantization, KV-cache quantization, and sub-4-bit quantization for LLMs and generative AI models  Build tooling to analyze, profile, and debug model accuracy degradation caused by quantization  Integrate AIMET workflows with popular ML frameworks — PyTorch and ONNX  Develop APIs and developer-facing tooling to make AIMET accessible and easy to use for external customers and design partners  Integrate AIMET to enable Quantization at large scale.  Own end-to-end quantization and optimization of models, ensuring they meet accuracy, latency, and power targets on Qualcomm hardware  Quantize and validate a broad range of model families — vision transformers, LLMs, diffusion models, speech, and multimodal architectures Develop and maintain automated quantization pipelines and evaluation harnesses to scale model onboarding Minimum Qualifications: • Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience. OR Master's degree in Computer Science, Engineering, Information Systems, or related field and 3+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience. OR PhD in Computer Science, Engineering, Information Systems, or related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.

3+ years of industry experience in machine learning, deep learning, or AI infrastructure  Strong proficiency in Python, with hands-on experience in PyTorch, ONNX and/or TensorFlow  Solid understanding of neural network architectures — CNNs, Transformers, LLMs, diffusion models, multimodal models  Experience with model quantization techniques — PTQ, QAT, weight-only quantization, mixed-precision, sub-4-bit methods  Hands-on experience quantizing LLMs (GPT, LLaMA, Mistral, Falcon, or similar families) for inference optimization  Familiarity with AIMET, GPTQ, AWQ, SmoothQuant, or similar quantization frameworks is a strong plus  Experience working with ONNX, TFLite/LiteRT, or other model interchange formats  Understanding of hardware constraints: memory bandwidth, compute precision (INT4/INT8/FP16/BF16), and NPU/DSP execution  Experience collaborating across teams or BUs to