Talent.com
This job offer is not available in your country.
Model Service and Innovation Engineer

Model Service and Innovation Engineer

China Mobile International LimitedKuala Lumpur, Kuala Lumpur, Malaysia
21 hours ago
Job description

Get AI-powered advice on this job and more exclusive features.

Direct message the job poster from China Mobile International Limited

Responsibilities

  • Responsible for optimizing, compressing, and accelerating trained large models, and deploying them as high-performance inference services.
  • Design and optimize inference service deployment architecture to improve performance, reduce costs, and ensure the efficient operation of models in the Intelligent Computing Center.
  • Develop core components of the model service platform (MaaS) to promote automated deployment, elastic scaling, and service governance.
  • Keep track of new large models and algorithm technologies, explore innovative application scenarios, and promote their engineering implementation.
  • Participate in technical docking with vendors and customers and provide model service solutions and performance optimization support.
  • Write technical documents to support platform productization and continuous iteration.

Qualifications

  • Bachelor\'s degree or above in Computer Science, Artificial Intelligence, Software Engineering, or related majors.
  • Proficiency in English, capable of reading cutting-edge papers and international technical documents, and supporting cross-border collaboration.
  • Familiar with mainstream deep learning frameworks (PyTorch, TensorFlow) and model inference tools (TensorRT, ONNX Runtime, OpenVINO, etc.).
  • Master model compression and optimization technologies (quantization, distillation, pruning, parallel inference).
  • Have experience in developing large-scale distributed inference and service-oriented architectures (Kubernetes, microservices).
  • Familiar with GPU / heterogeneous acceleration (CUDA, ROCm, domestic GPU SDK) and high-performance computing optimization.
  • Experience in cloud-native R&D (K8s, Docker, service mesh Istio, etc.) is preferred.
  • Experience in researching large model application innovation (AIGC, intelligent customer service, industry AI solutions) is preferred.

    • Seniority level

  • Mid-Senior level

    • Employment type

  • Full-time

    • Job function

  • Information Technology

    • Industries

  • Telecommunications

    • #J-18808-Ljbffr

    Create a job alert for this search

    Service Engineer • Kuala Lumpur, Kuala Lumpur, Malaysia