Scientific Assistant / Scientific Assistantess

Introduction

The Biomedical Image Computing Group develops algorithmic solutions aimed at enabling the automatic interpretation and enhancement of biomedical images, striving to increase efficiency and accuracy in both clinical practice and research.

Project Background

The enhancement of endoscopic videos is a critical yet complex task. These videos play an integral role in various clinical interventions where the clarity of imaging data is essential for procedural success. However, challenging imaging conditions can significantly compromise the quality of endoscopic videos due to various artifacts. This project seeks to develop the next generation of enhancement algorithms specifically tailored for endoscopic videos, focusing on applications in real-time interventions. Development efforts will prioritize enhancement quality and computational efficiency, particularly regarding latency.

The successful candidate will join the BMIC team at ETH Zurich and will also be part of the Computer Vision Lab (CVL). This project is conducted in collaboration with an industrial partner, who will provide support with hardware and software integration.

The position is available immediately and is initially limited to 8 months.

Job Description

This position involves the implementation, optimization, and deployment of deep-learning image enhancement models for real-time operation. Rather than focusing solely on model training, the successful candidate will work on translating existing and new architectures into efficient real-time processing pipelines directly connected to an industrial camera system. Typical tasks will include:

• Profiling and optimizing models for low-latency inference.
• Implementing and adapting neural-network architectures with real-time constraints in mind.
• Integrating camera acquisition and preprocessing pipelines.
• Contributing to project deliverables and scientific manuscript preparation.

Your Profile

• MSc degree in computer science, machine learning, medical image computing, or a related field.
• Familiarity with neural-network-based image processing pipelines.
• Excellent programming skills and experience with Python.
• Experience implementing and validating neural-network architectures using PyTorch.
• Demonstrable experience with model deployment/acceleration (PyTorch, ONNX, TensorRT, CUDA/C++, etc.), profiling tools, along with camera/sensor integration is a plus.

What We Offer

Your job will have a significant impact: Become part of ETH Zurich, which not only supports your professional development but also actively contributes to positive societal change. You can expect numerous benefits, including public transport season tickets, car sharing, a wide range of sports offered by the ASVZ, childcare services, and attractive pension benefits.

Curious? So Are We!

Apply online using the form below. Only applications matching the job profile will be considered.

Further information about Biomedical Image Computing can be found on our website.