Machine Lerning Engineer (Internship)

Magnes AG is an ETH Zurich spinoff based in Zurich, Switzerland. We focus on analyzing human movements and providing real-time feedback to individuals with mobility or neurological challenges by integrating AI algorithms and wearable sensors. Using our flagship product, NUSHU, we are developing therapeutic exergames to enhance mobility and independence in older adults and patients undergoing physiotherapy or rehabilitation.

We are looking for a Machine Learning Engineer intern or Master’s thesis student to play a crucial role in the development of innovative deep learning algorithms for therapeutic exergames. Gain hands-on experience in machine learning, wearable technology, and human-computer interaction while contributing to impactful projects that improve the quality of life for older adults.

Keywords: machine learning, data analysis, wearables, digital health, human-computer interaction, edge computing

• Currently enrolled in a Master’s program in Computer Science, Data Science, Biomedical Engineering, or a related technical field
• Strong motivation and enthusiasm for applying machine learning to healthcare and digital health applications
• Programming experience in Python and familiarity with machine learning frameworks (e.g., PyTorch, TensorFlow, scikit-learn)
• Basic understanding of machine learning concepts and data analysis
• Good communication skills in English (German is a plus but not required)
• Ability to work independently and collaborate effectively in a team environment

As a Machine Learning Engineer intern or Master’s thesis student at Magnes AG, you will play a crucial role in the development of innovative machine learning algorithms for therapeutic exergames. Exergames (EG), which integrate gaming elements into exercises, present a promising and cost-effective approach for delivering motor-cognitive dual-task training, particularly in home settings.

For an exergaming system to be effective in physiotherapy and rehabilitation, it should adapt exercises to users’ capabilities and needs, provide multimodal feedback (e.g. visual, auditory, haptic) on exercise execution and quality, and monitor progress over time. However, most existing EGs focus on a limited set of exercise tasks, offer only basic difficulty adjustments, and prioritize primary goals (e.g., task completion) at the expense of secondary goals (e.g., movement quality).

Core task involve:

• Analyze sensor data from wearable devices and state-of-the-art motion capture systems to model human movement during exercise.
• Develop and deploy machine learning algorithms for real-time monitoring and feedback in exergaming applications.
• Draw insights from clinical assessments and user studies to assess exercise performance and adapt training protocols.

• Opportunity to work in a tech start-up with a multi-national and interdisciplinary team
• Get involved in the R&D activities with challenging and interesting technical and scientific problems
• Flexible working hours
• 25 days of vacation