Description

You will design and implement algorithms to detect and identify on-screen graphics within live video streams.

Responsibilities

• Develop and fine-tune machine learning models for pattern recognition, segmentation, and graphics transformation.
• Implement OCR systems to extract text from graphics.
• Ensure real-time processing capabilities for live feeds without compromising performance.
• Integrate models into production systems to ensure scalability and reliability.
• Research state-of-the-art computer vision techniques for video analysis, graphics replacement, and text translation.

Required Skills

• 3+ years of experience in computer vision or related fields.
• Proficiency in Python and/or C++ for implementing vision pipelines.
• Hands-on experience with TensorFlow, PyTorch, or OpenCV.
• Experience detecting patterns, segmenting visual components, or replacing graphical content in images or video.
• Knowledge of OCR tools like Tesseract or advanced text recognition techniques.
• Familiarity with translation APIs or NLP frameworks such as Hugging Face Transformers or Google Translate API.
• Strong understanding of image/video processing, segmentation, and feature extraction.
• Bachelor's or Master's degree in Computer Science, Data Science, Computer Vision, or a related field.

Preferred Skills

• Experience with video processing frameworks or real-time media pipelines.
• Understanding of multi-language support in OCR and translation systems.
• Knowledge of deep learning models for real-time graphics manipulation.
• Background in broadcasting or live sports production.

Key Skills

Education

Bachelor’s or Master’s degree