Senior AI/ML Engineer (IRC276364)

Job Description:

• Bachelor's in software engineering, Electrical/Electronics Engineering, or related field
• At least 6-8 years of progressive experience in software development with a focus on AI/ML techniques
• Strong experience in developing and fine-tuning ML models
• Experience hands-on with one or more of the following: Open3D or MeshLab or Blender or Ansys
• Knowledge and experience with U-Net or CNN for image analysis and segmentation
• Experience with Data Cataloging, Data setup in S3 – EDA on data and pipelining for SageMaker
• Strong programming skills in Python and C++ programming 
• Experience with scripting languages such as Shell, Batch, Bash and Linux commands
• Strong analytical skills, capable of uncovering anomalies in robust software
• Experience with Windows and Linux operating systems
• Experience with JIRA or any similar bug tracking tools

Expert in AI/ML computer vision techniques to develop intelligent systems capable of automatically segmenting surgical videos into distinct phases, identifying critical moments, and recognizing surgical instruments and techniques.

• Has experience hands-on with one or more of the following: Open3D or MeshLab or Blender or Ansys
• Has knowledge and experience with U-Net or CNN for image analysis and segmentation
• Has experience with Data Cataloging, Data setup in S3 – EDA on data and pipelining for SageMaker

This role requires expertise in deep learning frameworks (e.g., TensorFlow, PyTorch), computer vision libraries, and cloud-based AI services (like AWS SageMaker or Google Cloud AI), along with a strong understanding of surgical procedures and medical terminology.

Capable of developing user-friendly interfaces for surgeons to interact with the AI-generated insights.

Job Responsibilities:

• Designing and implementing deep learning models for real-time video analysis.
• Creating automated annotation systems that label procedures, instruments, and anatomical structures.
• Developing algorithms to extract quantifiable metrics from surgical performances.
• Working on a task related to the measurement of dimensions in images

Department/Project Description

Join us to build the connected vision intelligence layer that unifies surgical imaging, robotics, and data services across the operating room portfolio spanning endoluminal, orthopedics, and the next-gen general-surgery platform, while powering the digital ecosystem in hospitals. You’ll help transform raw surgical video and device signals into real-time insights, collaborative telepresence, and longitudinal case intelligence used before, during, and after procedures. First product releases include surgical video editing/publishing and telepresence, rolling out to select sites in the near future. Your work will directly accelerate that journey and connect robotic vision to the OR and hospital digital platform