Internship - Experimental Data Science for Gas Sensing and Time-Series Analytics

Become familiar with vacuum technology, gas dynamics, process chambers, and sensor systems. Support the setup and execution of experiments in our vacuum test laboratory. Plan experiments using a structured Design of Experiments approach. Collect and organize multivariate time-series data from different sensor technologies. Develop data-preprocessing workflows for synchronization, filtering, segmentation, outlier handling, and data-quality assessment. Explore the relationships between sensor signals, gas properties, and process conditions. Develop and compare data-driven methods. Validate the developed methods using independent experiments and different operating conditions. Document experimental procedures, datasets, modelling methods, results, and limitations. Present your findings and potential next steps to engineers and researchers.

At VAT, we change the world with vacuum solutions. As the world’s leading supplier of high-performance vacuum valves, we have been driving innovation for more than 60 years. With over 3,200 employees worldwide, we operate from our headquarters in Haag, Switzerland, with manufacturing sites in Switzerland, Malaysia and Romania, as well as sales and service hubs around the world. We are guided by our passions integrity, teamwork, customer centricity, and innovation – always working together as #oneVAT. Joining us means becoming part of a passionate, international team where your voice is heard, your ideas matter, and your career growth is supported.

• MSc student or recent graduate in Data Science, Machine Learning, Physics, Mathematics, Mechanical Engineering, Electrical Engineering, Chemical Engineering, Control Engineering, Mechatronics, or a related field.

• Basic knowledge of data analysis, statistics, signal processing, and machine learning.

• Programming experience in Python, MATLAB, or similar data analysis tools.

• Experience or interest in time-series data analysis, sensor-data analytics, feature engineering, and model validation.

• Interest in combining experimental laboratory work with data-driven modelling.

• Willingness to work hands-on with vacuum equipment, sensors, and data-acquisition systems.

• Experience with machine learning frameworks such as scikit-learn, PyTorch, or TensorFlow is an advantage.

• Knowledge of Design of Experiments (DoE), laboratory measurements, or uncertainty estimation is a plus.

• Strong analytical thinking, independent learning ability, and a collaborative mindset.

• Interest in vacuum technology, gas sensing, process control, or semiconductor manufacturing.

• Good written and spoken English.