Computer Vision Engineer

Position Summary

The Computer Vision Engineer will be responsible for leading the development of advanced navigation and guidance solutions for robotic-assisted surgeries.

Essential Functions

• Work closely with clinical experts, system engineers, software and hardware engineers, and regulatory specialists to create a high-accuracy, real-time navigation and surgical guidance system that integrates seamlessly into the surgical environment
• Work with surgical navigation team that is responsible for designing and developing advanced navigation and guidance solutions for robotic-assisted surgeries
• Work closely with clinical specialists to translate surgeon feedback into technological improvements and user interface enhancements
• Design and implement real time vision algorithms to account for surgical instruments and anatomical structures, adapting pre-op imaging to intra-op imaging
• Develop novel machine vision sensors and extended reality display systems that help track instrument positions
• Collaborate with product, system, and hardware teams to evaluate, select, and integrate depth sensors (e.g., structured light, Time-of-Flight, stereo cameras) or multi-modal systems (e.g., near-infrared or ultrasound) to capture surgical site geometry or anatomical structures
• Ensure robust calibration and synchronization of multiple sensors if needed
• Develop and maintain code in a real-time environment, ensuring modularity, scalability, and reliability (e.g., C++/Python with GPU acceleration where appropriate)
• Define and execute test plans for accuracy, reliability, and performance of the tracking system using synthetic, phantom and cadaver experimental data
• Document results to support risk management, regulatory filings, and product development milestones
• Engage in the entire product life cycle from research to initial requirements drafting to sustaining efforts

Qualifications

• Requires a Master’s degree or foreign equivalent in Computer Science, Information Technology, Data Science, Robotics, or a related field
• 3 years of experience in a related occupation
• Experience using 3D vision algorithms (object pose estimation, features extraction, optical flow)
• Experience programming in C++ and Python, with hands on experience with open source and libraries like OpenCV, Open3D or equivalent
• Experience with deep-learning frameworks (e.g., PyTorch, TensorFlow) for vision tasks
• Experience with GPU programming (CUDA) or parallelization frameworks
• Experience optimizing machine learning models using multi-threading, GPU, and machine learning frameworks, such as Tensorflow
• Experience analyzing and improving the reliability, stability, and performance of the prototype hardware in connecting with various devices
• Experience with computer vision algorithms, artificial intelligence algorithms, 3D geometry, integration with camera-based systems