Computer Vision: Traffic Scene Understanding
Computer Vision: Traffic Scene Understanding (Job Number: P17INT-21)
Mountain View, CA

This title includes multiple positions which offer the opportunity to conduct innovative research in computer vision, machine learning, and video analytics.  The candidate is expected to work on one of the following topics:

  • Human behavior understanding, including human pose estimation, action detection, intention prediction, and trajectory forecasting
  • Captioning and retrieval of traffic scene events from video
  • Automatic classification of various driving conditions and scenarios including place, weather, and traffic condition
  • Detection and prediction of traffic participant actions from video



  • PhD or highly qualified MS candidate in computer science, electrical engineering, or related field
  • Research experience in machine learning, computer vision and/or driver behavior data analytics
  • Highly proficient in software engineering using C++ and Python


Preferred Qualifications:

  • Experience in open-source Deep Learning frameworks such as TensorFlow or Caffe
  • Familiarity with graphical models (e.g. probabilistic graphical models, scene graphs)
  • Strong written and oral communication skills including development and delivery of presentations, proposals, and technical documents​​​​​