Computer Vision

At Cosmo, we are at the forefront of revolutionizing healthcare through our groundbreaking technology. With our innovative advancements in live endoscopy, we are transforming the landscape of medical diagnostics. We leverage AI to empower physicians, enabling them to make well-informed decisions and significantly improve the lives of their patients. Our dedication to excellence has resulted in creating GI Genius: our AI-enabled medical device for live endoscopy has received FDA approval and is successfully deployed in hospitals worldwide, making a significant impact in the field of healthcare. Check out our website for more information at As a Computer Vision & AI Scientist at Cosmo MedTech AI, you will design, implement, train and validate advanced deep learning models for video-based colonoscopy, contributing to AI products already deployed in hospitals worldwide. In this role, you will collaborate closely with other AI scientists and with data, software, and hardware teams to push the boundaries of the current state of the art and develop AI solutions that enhance real-time clinical performance and improve patient care. If you are passionate about artificial intelligence, computer vision, and healthcare, and want to see your work make a real impact in clinical practice globally, this is the perfect opportunity for you. The level of seniority for this position will be evaluated during the interview process, based on the candidate’s experience and expertise. Key Responsibilities Actively collaborate with other AI scientists and cross-functional teams to develop and implement AI solutions for medical endoscopy. Research, implement, train and evaluate advanced computer vision and deep learning approaches for endoscopy video analysis. Design rigorous experimental protocols and benchmark approaches efficiently on large-scale video datasets. Report findings clearly and effectively through internal reports, presentations, and technical documentation. Stay up to date with the latest advancements in computer vision, deep learning, and medical image analysis, and support the team’s continuous learning and scientific publications in top-tier conferences and journals. Support the integration of developed AI models into existing medical devices and systems. Contribute to internal code quality through code reviews and reproducible research practices. Required Skills Master’s degree in Computer Science, Engineering, Physics, Math or related; PhD strongly preferred (CV/ML/Medical Imaging). 5+ years of hands‑on experience in deep learning and computer vision (industry or academia); at least part of it on detection/segmentation, tracking and classification problems. Strong proficiency in Python and PyTorch; good software engineering practices (Github/Gitlab). Proven track record of working on innovative computer vision projects resulting in scientific publications, patents or public repositories. Excellent analytical, problem‑solving, and communication skills, with a collaborative mindset and the ability to work effectively both independently and as part of a team. Fluency in English (written and spoken) Nice to Have Previous work on medical image analysis or endoscopy. Publications or substantial contributions to projects accepted at top computer vision or medical imaging venues (e.g., CVPR, ICCV, MICCAI). Experience with transformer‑based architectures for image and video understanding (object detection, segmentation, tracking and classification), Experience with self‑supervised learning and large‑scale distributed training. Experience with depth estimation, surface reconstruction, or 3D geometry understanding from monocular video. Physical Requirements Expected travel is 30% Equal Opportunity Statement We support equal opportunities, without any discrimination; The research complies with Legislative Decree 198/2006 Seniority level Mid‑Senior level Employment type Full‑time Job function Information Technology and Science Industries Software Development and Medical Equipment Manufacturing #J-18808-Ljbffr