Scientific Assistant – Real-Time Generative Models / Computer Vision

ETH Zurich; Zürich; On-site; CHF 70,000 - 100,000; Full time

Benefits offered by this job

Public transport tickets

Childcare support

Pension benefits

Job summary

ETH Zurich's Biomedical Image Computing Group seeks a MSc student or graduate to implement, optimize, and deploy deep-learning image-enhancement models for real-time endoscopic video processing. You will translate architectures into efficient pipelines linked to an industrial camera system.

The role focuses on low-latency inference, profiling tools, and adapting networks to strict timing constraints, with collaboration across BMIC and CVL and opportunities to contribute to manuscripts and

Qualifications

• MSc degree or equivalent in CS/ML/medical image computing or related field.
• Familiarity with neural-network-based image processing pipelines.
• Excellent Python programming skills.
• Experience with PyTorch implementations of NN architectures.
• Experience with model deployment/acceleration and camera integration is a plus.

Responsibilities

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

Skills

Python

Neural networks

Real-time processing

Model deployment

Education

MSc degree in computer science, machine learning, medical image computing, or related field

Tools

PyTorch

TensorRT

ONNX

CUDA/C++

Job description

The Biomedical Image Computing Group develops algorithmic solutions to enable automatic interpretation and forming of biomedical images, aiming to increase efficiency and accuracy in clinical practice and research.

Project background

The enhancement of endoscopic videos is a critical yet complex task. These videos are integral to various clinical interventions, where the clarity of imaging data is essential for procedural success. Due to challenging imaging conditions, the quality of endoscopic videos can be significantly compromised by a range of artifacts. This project seeks to develop the next generation of enhancement algorithms tailored for endoscopic videos, with a focus on applications in real-time interventions. Development efforts will prioritize both enhancement quality and computational efficiency, particularly with respect to latency.

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

The position is open immediately and 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 primarily on model training, the successful candidate will work on translating existing and new architectures into efficient real-time processing pipelines connected directly 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, and contributing to project deliverables and scientific manuscript preparation.

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, and camera/sensor integration is a plus.

We offer

• Your job with impact: Become part of ETH Zurich, which not only supports your professional development, but also actively contributes to positive change in society
• You can expect numerous benefits, such as public transport season tickets and car sharing, a wide range of sports offered by the ASVZ, childcare and attractive pension benefits

Working, teaching and research at ETH Zurich

We value diversity and sustainability

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit Equal Opportunities and Diversity website to find out how we ensure a fair and open environment that allows everyone to grow and flourish. Sustainability is a core value for us – we are consistently working towards a climate-neutral future.

About ETH Zürich

ETH Zurich is one of the world’s leading universities specialising inscience and technology. We are renowned for our excellent education,cutting-edge fundamental research and direct transfer of new knowledgeinto society. Over 30,000 people from more than 120 countries find ouruniversity to be a place that promotes independent thinking and anenvironment that inspires excellence. Located in the heart of Europe,yet forging connections all over the world, we work together todevelop solutions for the global challenges of today and tomorrow.