Project Engineer in AI-Based Condition Monitoring

ETH Zurich seeks a Project Engineer for an AI-driven condition monitoring initiative, focusing on predictive maintenance for safety-critical mechanical systems through hybrid modeling and experimental validation.

This position supports a funded innovation project involving a Swiss industrial partner. The role centers on applying sensor-based and model-based techniques to assess the real-time condition and predict the maintenance needs of safety-critical mechanical systems. It blends rigorous academic research with practical engineering, providing strong prospects for professional development in applied R&D.

Responsibilities

• Construct hybrid models that integrate physical principles with data-driven approaches for assessing system health and predicting remaining useful life.
• Design and test artificial intelligence algorithms to detect degradation patterns within multisensor data streams.
• Establish end-to-end data pipelines covering acquisition, preprocessing, synchronization, annotation, and model training.
• Assemble and verify sensor-based laboratory test rigs and conduct experimental studies.
• Implement and validate the developed methodologies within an industrial setting.

Requirements

• Hold citizenship from Switzerland, the EU, or EFTA, or possess a valid Swiss work permit.
• Have a Master’s degree in mechanical engineering, mechatronics, robotics, computer science, or a closely related discipline from ETH or another university.
• Demonstrate prior experience in machine learning, computer vision, signal processing, or condition monitoring.
• Show strong programming proficiency in Python, particularly when handling experimental data.
• Be fluent in both German and English.

What the company offers

• Gain unique experience at the convergence of AI, sensor technology, mechanical modeling, and industrial experimentation.
• Access excellent growth opportunities in applied research and development.

About the company

ETH Zurich fosters an environment where multisensor data, AI methods, physical models, experiments, and industrial validation intersect to drive innovation.

• Work involves a multidisciplinary approach combining data analysis, AI, physical modeling, and hands-on experimentation.