Theme

Language

Global EN
Sweden ENSV
India EN

AI Software Engineer

Technology, Data & Digital · Data, AI & Analytics · Machine Learning · Software Engineering

In short

We are seeking an experienced AI Model Optimization Engineer for our team in Guangdong, China, focusing on the enablement, optimization, and deployment of AI models on edge platforms. The role involves the full model lifecycle, from architecture analysis and quantization to on-device deployment and performance tuning, with a focus on emerging architectures like LLMs and Diffusion Models.

Responsibilities

  • Enable and optimize state-of-the-art AI models for on-device deployment, focusing on performance, memory efficiency, and accuracy.
  • Develop and improve automated and intelligent model onboarding, conversion, deployment, and optimization pipelines.
  • Perform end-to-end model enablement, including export, graph transformation, quantization, compilation, runtime execution, profiling, and optimization.
  • Analyze performance bottlenecks across the model, software stack, and hardware accelerator for optimization opportunities.
  • Explore optimization techniques for emerging model architectures like LLMs, VLMs, LVMs, Diffusion Models, and MoE models.
  • Investigate platform-aware and hardware-aware model optimization using compute architecture and platform characteristics.
  • Evaluate new model architectures and AI technologies, translating research into practical deployment solutions.
  • Collaborate with cross-functional teams (engineering, research, product, customer-facing) for real-world AI model optimization.

Requirements

  • Master's degree or above in Computer Science, Artificial Intelligence, Electrical Engineering, or a related field.
  • Relevant industry experience in AI/ML model development, optimization, or deployment.
  • Strong understanding of deep learning fundamentals and modern model architectures (Transformers, large-scale generative AI).
  • Strong hands-on experience with PyTorch and common model formats/frameworks like ONNX.
  • Experience with model quantization (INT8/INT4, PTQ/QAT).
  • Hands-on experience with model export, conversion, quantization, deployment, and on-device execution.
  • Solid understanding of model performance optimization (latency, throughput, memory, accuracy trade-offs).
  • Strong Python programming and debugging skills.
  • Strong analytical and problem-solving skills for complex model and system issues.

Desired Qualifications

  • Hands-on experience optimizing LLMs, VLMs, Diffusion Models, or MoE models.
  • Experience with AI model deployment and optimization on edge or heterogeneous computing platforms (CPU, GPU, NPU, DSP).
  • Experience with advanced low-bit quantization methods (INT4/INT2, mixed-precision, GPTQ, AWQ, SpinQuant).
  • Experience with performance profiling and system-level optimization across model architecture, compiler, runtime, and hardware.
  • Understanding of hardware architecture and platform characteristics for model-level optimization.
  • Experience developing automated model onboarding, deployment, benchmarking, or optimization pipelines.
  • Research experience in model compression, quantization, efficient AI inference, or related areas.
  • Publications, patents, or open-source contributions in relevant AI fields are a plus.
  • Bachelor's degree in Engineering, Information Systems, Computer Science, or related field.

Benefits

  • Qualcomm is an equal opportunity employer.
  • Commitment to providing accessible processes and reasonable accommodations for individuals with disabilities during the application/hiring process.
  • Commitment to making the workplace accessible for individuals with disabilities.

Skills

PyTorchONNXPython
#AI#LLM#VLM#LVM#Diffusion Models#MoE models#Quantization#Edge AI#Deployment#Optimization
Qualcomm Logo

About Qualcomm

Enabling a world where everyone and everything can be intelligently connected.

Enabling a world where everyone and everything can be intelligently connected.\n\n

Qualcomm Logo

Company

Qualcomm

Job Posted

5 days ago

Employment Type

Full Time

Work mode

On Site

Experience Level

Mid-Senior

Locations

China

Qualification

Master, Bachelor, Doctoral

Applicants

Be an early applicant