Skip to contentSkip to footer
  • Community
  • Jobs
  • Companies
  • Salaries
  • For employers
      Notifications

      Loading...

      Elevate your career

      Discover your earning potential, land dream jobs, and share work-life insights anonymously.

      employer cover photo
      employer logo
      employer logo

      Sportradar

      Is this your company?

      About
      Reviews
      Pay and benefits
      Jobs
      Interviews
      Interviews
      Related searches: Sportradar reviews | Sportradar jobs | Sportradar salaries | Sportradar benefits
      Sportradar interviewsSportradar Senior Computer Vision Engineer interviewsSportradar interview


      Glassdoor

      • About / Press
      • Awards
      • Blog
      • Research
      • Contact Us
      • Guides

      Employers

      • Free Employer Account
      • Employer Centre
      • Employers Blog

      Information

      • Help
      • Guidelines
      • Terms of Use
      • Privacy and Ad Choices
      • Do Not Sell Or Share My Information
      • Cookie Consent Tool
      • Security

      Work With Us

      • Advertisers
      • Careers
      Download the App

      • Browse by:
      • Companies
      • Jobs
      • Locations
      • Communities
      • Recent posts

      Copyright © 2008-2026. Glassdoor LLC. "Glassdoor," "Worklife Pro," "Bowls" and logo are proprietary trademarks of Glassdoor LLC.

      Company Bowl sample

      Want the inside scoop on your own company?

      Check out your Company Bowl for anonymous work chats.

      Bowls

      Get actionable career advice tailored to you by joining more bowls.

      Followed companies

      Stay ahead in opportunities and insider tips by following your dream companies.

      Job searches

      Get personalised job recommendations and updates by starting your searches.

      Top companies for "Compensation and Benefits" near you

      avatar
      GHG Corp
      3.7★Compensation and benefits

      Senior Computer Vision Engineer Interview

      25 Feb 2022
      Anonymous interview candidate
      Ljubljana
      No offer
      Positive experience
      Average interview

      Application

      I applied online. The process took 3 weeks. I interviewed at Sportradar (Ljubljana) in Feb 2022

      Interview

      The entire process took about 3 weeks. The interviewers were friendly and I felt that they wanted to get to know me as a person. I had 3 interviews, introductiory, behavioral and one technical. I was also given a task to complete within a week. The task was to develop a tennis scoreboard reader from a live broadcast of a match. I had to locate the scoreboard's bounding box and extract the player names, server indicator, and score. At the technical meeting, we first discussed my solution to the task and then there were a number of computer science related question in the field of algorithms, data structures, signal processing, deep learning. Nothing too detailed, more of a high level overview. They also presented me with the problem they are solving and wanted me to elaborate on how would I approach it. I had to open my python IDE (I use PyCharm) and had to write some code which involved function declaration with type definitions, usage of slicing with numpy, making a new branch on git.

      Interview questions [9]

      Question 1

      How would you detect when a player kicks a ball just from a video?
      Answer question

      Question 2

      Computational complexity of hash map- best worst? What type of sorting algorithms do you know? Their time complexity?
      Answer question

      Question 3

      What kind of deep learning architectures do you know of? Do you know ResNet? Transformers?
      Answer question

      Question 4

      What loss functions can be used for classification, segmentation, regression?
      1 Answer

      Question 5

      How is convolution on images performed? How can it be done for large kernels and large images?
      1 Answer

      Question 6

      Do you know of template matching for object detection?
      Answer question

      Question 7

      What problems can we encounter in very deep neural networks?
      1 Answer

      Question 8

      How is plane to plane matching done in multiple cameras setup?
      Answer question

      Question 9

      Describe how a scale-invariant feature transform works.
      Answer question
      1
      avatar
      Sportradar response
      2y
      Thank you for your positive review! We're thrilled to hear about your great experience with us. Your feedback truly inspires us to keep striving for excellence. You can contact us at any time at info@sportradar.com. Thanks again for interviewing with us! Sincerely, Sportradar People Team