Python / Computer Vision Engineer (tracking module, sports video analytics)

Company: United Developers

We are United Developers, an international IT company with over 10 years of experience in developing and supporting mobile solutions for clients from Europe and USA. Our key expertise is creating complex mobile applications for IoT (Internet of Things) and integrating AI/ML into products for businesses and startups.

Format: remote, project-based work. Payment: fixed fee per module. Employment: Preferably full-time or 20-30h.

About the project: We are developing a system for automatic tracking and shooting of sports matches (computer vision). The main pipeline is ready, the detection model is being trained by a separate specialist. We are looking for an engineer who will assemble the tracking logic around the finished model and bring the module to a working state.

Tasks:

• Build a video processing pipeline: detection → tracking → framing zone selection
• Implement object tracking logic (ByteTrack or similar) and multi-object player tracking.
• Develop hybrid logic for determining the active game zone: tracking by player center of mass + switching focus to an individual player in key game situations.
• Integrate the ready-made detection model (trained separately) into the overall pipeline.
• Optimize for working with real match recordings.

Requirements:

• Proficient Python, experience in Computer Vision.
• Practical experience with object tracking (ByteTrack, DeepSORT, SORT, or similar).
• Understanding of the limitations of tracking algorithms and the ability to design logic around them.
• Experience with object detection (YOLO and similar).
• Ability to explain how the task will be solved, not just "I know the framework".

Will be a plus:

• Experience with sports video analytics or tracking in complex scenes (occlusions, object loss).
• Experience in building CV solution architecture.