Scientific Assistant - Real-Time Generative Models

About the role

The Biomedical Image Computing Group at ETH Zurich develops algorithmic solutions for the automatic interpretation and formation of biomedical images, improving efficiency and accuracy in clinical practice and research. The project aims to create next-generation enhancement algorithms for endoscopic videos used in real-time interventions, balancing image quality with low latency. The position is open immediately, initially for 8 months, and the candidate joins the BMIC team and the Computer Vision Lab (CVL), with an industrial partner supporting hardware and software integration.

Key responsibilities

• Implement, optimize and deploy deep-learning image-enhancement models for real-time operation
• Translate existing and new architectures into efficient real-time processing pipelines connected to an industrial camera system
• Profile and optimize models for low-latency inference
• Implement and adapt neural-network architectures under real-time constraints
• Integrate camera acquisition and preprocessing pipelines
• Contribute to project deliverables and scientific manuscript preparation

Required profile

• MSc degree in computer science, machine learning, medical image computing or a related field
• Familiarity with neural-network-based image processing pipelines
• Demonstrable experience deploying and accelerating models (PyTorch, ONNX, TensorRT, CUDA/C++) and integrating cameras or sensors is a plus

Required skills

• Excellent programming skills and experience with Python
• Experience implementing and validating neural-network architectures with PyTorch

What we offer

• Public transport season tickets and car sharing
• Sports offered by the university association, childcare and pension benefits

Applications are submitted online only, with a CV and a recommendation letter if available.