Computer Vision Engineering Intern - Fall 2026

Primary Function of Position

The candidate will join a leading R&D team to advance research and development in cutting-edge computer vision for robotic endoscopic video technologies. The focus will be on vision foundation/diffusion models, feature detection, and multimodal video analysis, contributing to next-generation AI platforms for real-world applications. We are seeking a talented individual passionate about the latest advancements in computer vision and deep learning.

Essential Job Duties

• Explore and experiment with state-of-the-art computer vision models, including foundation models and generative diffusion models, with applications to video understanding, multi-modal data, and visual feature extraction.
• Prototype novel algorithms and evaluate performance using public and proprietary datasets.
• Conduct literature surveys and summarize key findings in reports and presentations.

Qualifications

• Solid understanding and hands-on experience in computer vision, deep learning, and video analysis.
• Knowledge in one or more areas: large vision-language models, generative diffusion models, feature detection, scene understanding, video classification, or multimodal learning.
• Proficiency in programming with Python or C++, with experience in relevant frameworks (e.g., PyTorch, OpenCV, DINO/CLIP, HuggingFace Transformers, etc.).
• Strong research and communication skills, with the ability to summarize findings and present them clearly.
• Passionate about pushing the boundaries of AI technologies to solve complex, real-world problems.
• Passion for developing technologies to improve the lives of patients and physicians.
• Self-driven, able to work independently and deliver rapid prototyping and experimentation.
• Able to perform fast prototyping iterations; thinking outside the box to solve practical problems.