Senior Artificial Intelligence Engineer

In this role you will design, optimize, and deploy deep learning models for surgical video analysis across edge and cloud platforms. You will work with cross-functional teams to push real-time computer vision capabilities that enhance patient care on a global scale. You’ll prototype quickly, benchmark performance, and drive end-to-end video processing pipelines that balance accuracy and latency. Your work helps advance Medtronic Digital Technologies’ mission to improve the standard of care in surgery. This is a hands-on, impact-focused opportunity in a fast-evolving field.

• competitive salary
• flexible benefits package
• short-term incentive (MIP)

• Design, benchmark, and optimize deep learning models for computer vision and video understanding
• Improve model architectures and inference pipelines to reduce latency and increase throughput while preserving accuracy
• Develop and productionize end-to-end video processing pipelines for surgical video analysis in cloud and/or edge environments
• Address temporal reasoning, motion understanding, and multi-frame video analysis problems
• Deliver high-quality, maintainable code and contribute findings in team discussions
• Stay current with advances in CV, video learning, and model optimization and contribute new ideas

• Master’s or PhD in Computer Science, Mathematics, Computer Vision, Machine Learning, or related field
• Hands-on experience designing, training, and evaluating deep learning models for computer vision using PyTorch
• Experience with video-based ML problems (video classification, action recognition, tracking, temporal modeling, multi-frame reasoning)
• Strong understanding of model optimization techniques (pruning, quantization, sparsity, knowledge distillation, architecture-level efficiency)
• Experience with AI optimization tools such as TensorRT
• Strong programming skills in Python and libraries (NumPy, scikit-learn, OpenCV)
• Ability to analyze performance bottlenecks and optimize across model, software, and hardware layers

• Strong communication and collaboration with engineers, clinicians, and stakeholders
• Proactive learning and sharing insights in cross-functional teams
• Result-oriented problem solving and ability to work in fast-paced environments
• PyTorch
• TensorRT
• Video understanding and computer vision