About

Sourav Bose is a skilled Applied Research Engineer at LinkedIn with a focus on Multimedia AI, Computer Vision, and Machine Learning. He is passionate about applying Deep Learning techniques to Computer Vision, Object Tracking, Object Segmentation, and Real-time 3D Reconstruction. With extensive experience in managing large volumes of Image and Depth data, he has successfully built commercial data-powered products. Sourav is a perpetual learner with excellent research skills and a patient approach to delivering results. He thrives on taking on new challenges and enjoys working in a diverse team. Currently, at LinkedIn, Sourav develops Deep Learning classifiers to flag NSFW Images/Videos and foundational AI models that serve as signals in other downstream use-cases. His work collectively ensures that LinkedIn remains a safe, relevant, and professional platform for its users. Prior to his role at LinkedIn, Sourav worked as a Senior Software Engineer - Research Development at Samsung Research Institute Bangalore. Here, he designed and developed end-to-end solutions in Augmented Reality / Virtual Reality for Camera Applications in premium mobile devices. His expertise includes Semantic Segmentation, Multi-modal object detection and tracking, Scene understanding w.r.t. Augmented Reality use-cases, Geometric and Deep Learning approaches for Multiview 3D Reconstruction, and Deployment of Vision solutions in Android platform. Sourav's previous experience also includes an internship at IIM Calcutta, where he worked with Prof. (Dr.) Ambuj Mahanti to develop a solution for text-based deviation pattern recognition in bank documents. He successfully implemented a GUI python app and integrated ML-based solutions for predicting risk scores. Sourav has a Master's Degree in Computer Science from the Indian Institute of Technology, Bombay, and a Bachelor of Technology (BTech) in Computer Engineering from Heritage Institute of Technology, Kolkata. He also has a High School degree in Science from B.D. Memorial International. Sourav's technical skills include Research Scientist, Computer Vision, AI, ML, Deep Learning, Corpus, Mobile, Object detection, Object Detection, Software Engineer, Android, and Python. He has relevant experience of 4.78 years.