Description
Your responsibilities
MLOps & Model Integration
- Deploy, monitor, and maintain machine learning models for surgical applications on HPC and edge devices within OR-X and ROSI research infrastructure
- Develop CI/CD pipelines for model lifecycle management, automated testing, and continuous deployment
- Leveraging NVIDIA technology for accelerating deployment of ML models
- Deployment of simulation environments
Data Engineering & Infrastructure
- Integrate multimodal data streams (video, kinematics, tracking, imaging, sensor data) into the central AI infrastructure
- Develop APIs, data ingestion pipelines, and real-time streaming frameworks
- Structure and pre-process multimodal surgical datasets for model training and downstream analytics
- Develop a distribution strategy that enables external researchers to access the data
AI Deployment in Surgical Workflows
- Work closely with AI researchers to operationalize models for surgical scene understanding, workflow prediction, skill assessment, and mixed reality
- Develop monitoring tools to ensure robustness, reliability, and latency compliance for real-time surgical applications
- Collaborate with robotics engineers to interface AI pipelines with devices accessible through ROS2 for control and visualization
System Testing & Validation
- Support verification and validation experiments in realistic ex-vivo settings
- Implement performance monitoring, logging dashboards, and evaluation frameworks for deployed AI models
- Contribute to guidelines and best practices for safe, reliable clinical translation of AI-enabled systems
Your profile
- Degree from University of Applied Sciences or higher in Computer Science, Electrical Engineering, Robotics, or a related field
- Strong experience in MLOps, including Docker, Kubernetes, CI/CD pipelines, model serving and workflow orchestration tools
- Strong programming skills in C++, Python, and related languages
- Experience with data engineering, data pipelines, and multimodal dataset handling
- Proficiency in interfacing with AI infrastructures, preferably with experience in NVIDIA AI technologies. Experience with Holoscan is an asset
- Familiarity with Nvidia hardware (DGX, Spark, Jetson)
- Experience with ROS2 and real-time systems
- Comfortable in Linux/Ubuntu environments, Git/GitHub workflows, and containerization
- Motivation to work in a translational, interdisciplinary environment connecting AI, robotics, and clinical research
- English is the main working language; German is an added advantage
What we offer
Our employees benefit from a wide range of attractive offers. More
Location
OR-X
Information on your application
What We Offer
- Active participation in a rapidly growing and internationally recognized Surgical Data Science ecosystem
- The opportunity to shape the next generation of AI-driven surgical technologies, integrating AR, robotics, and intelligent assistance systems
- A highly innovative environment at the intersection of engineering, AI research, and clinical practice at the University Hospital Balgrist
- Collaboration with leading academic and industrial partners (ETH AI Center, NVIDIA, Microsoft, ZHAW, and others)
- A supportive, motivated, and interdisciplinary team that values creativity, collaboration, and impact
Application
Please send your application to Dr. Fabio Carrillo (fabio.carrillo@balgrist.ch) with the following documents:
- Motivation letter (max. 1 page)
- Current CV
- Relevant project portfolio or GitHub (optional)
Further information
Questions about the job
Dr. Fabio Carrillo
Head of OR-X Research Unit
+41 44 510 32 64
Joinrocs@balgrist.ch
Working at UZH
The University of Zurich, Switzerland's largest university, offers a range of attractive positions in various subject areas and professional fields. With around 10,000 employees and currently 12 professional apprenticeship streams the University offers an inspiring working environment on cutting-edge research and top-class education. Put your talent and skills to work with us. Find out more about UZH as an employer!
j4id9992716a j4it1251a j4iy25a