Job Description

We are looking for talented and highly motivated engineers for OpenVINO GPU plugin development. OpenVINO (https://github.com/openvinotoolkit/openvino)is an open-source toolkit for optimizing and deploying AI inference on various HW platforms. You will be working on developing highly-optimized AI inference software for Intel GPU platforms, collaborating with global Intel teams.
Your responsibilities will include, but not be limited to:
  Analyze inference performance of various deep learning models on Intel GPU platforms, including large language models, diffusion models, and vision models
  Optimize inference performance on Intel GPU platforms based on the performance analysis
  Functionally enable new deep learning models on Intel GPU platforms
  Enable future Intel GPU platforms in the plugin
  Develop tools and debugging features for efficient analysis

• Qualifications
  
  Minimum qualifications are required to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.
  
  Minimum Qualifications:
    5+ years as a software engineer
    Excellent programming and debugging skills with modern C++ on Linux and Windows
    Strong computer science knowledge especially in data structure, algorithm, operating system, and computer architecture
    Good problem-solving and trouble-shooting skills with proactive mindset
    Good communication skills for collaboration
  
  Preferred Qualifications:
    Software development on GPU or AI accelerator with parallel computing
    Understanding of deep learning technologies
    Experience of large-scale software engineering projects
    Programming with Python
    English (both written and verbal)
  
  In this role, you will work as a hybrid way. You will basically work from home, but you will be also required to come to office regularly.