Staff Machine Learning Engineer – Model Optimization & Quantization

Company: Qualcomm Technologies, Inc. Job Area: Engineering Group, Engineering Group > Machine Learning Engineering General Summary:

Join the Qualcomm AI Hub team and help developers integrate machine learning into their products and experiences:   https://aihub.qualcomm.com/ .   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 in AI Hub Workbench Quantize job to enable Quantization at large scale.   Own end-to-end quantization and optimization of models published on Qualcomm AI Hub, 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 — for deployment via AI Hub   Develop and   maintain   automated quantization pipelines and evaluation harnesses to scale model onboarding across AI Hub's growing model catalog     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