

Job Description
We are seeking a self-motivated intern to support our AI Research and Development team in projects focused on developing a variety of AI foundation models based on multi-modal surgical data. This unique role focuses on the application of cutting-edge Visual-Language-Action (VLA) models and advanced robot learning techniques to enhance the capabilities of the da Vinci surgical system. The ideal candidate will bridge the gap between large-scale multimodal AI research and practical, high-impact applications in a safety-critical medical domain.
Essential Job Duties
• Conduct research and development on AI technology for surgical robotics, specifically integrating visual data (endoscopic video), surgical context (language/data), and precise robotic actions (instrument control).
• Develop and implement novel algorithms for VLA models focused on surgical scene understanding, procedure phase recognition, and learning from expert demonstrations (e.g., imitation learning) to improve system guidance and automation features.
• Analyze and process large, real-world surgical datasets from the da Vinci system to train and evaluate AI models.
• Validate models using both internal simulation platforms and, where appropriate, physical da Vinci systems, adhering to strict quality and regulatory protocols.
• Collaborate with a cross-functional team of engineers, researchers, and potentially even clinicians/surgeons, to translate research prototypes into robust, testable software solutions.
• Document research outcomes and contribute to technical reports and internal documentation, with potential opportunities for patent filings or conference submissions.
Industries: Medical Device
Function: Web Development
Job Skills
- Analytical Skills
- Statistics
- Technical Support
- Databases
- Tensorflow
- pytorch
Job Overview
Date Posted
Location
Offered Salary
Not disclosed
Expiration date
Experience
Qualification











