I’m an AI architect and technical lead in the AI & New Technologies team at Siemens, where I build enterprise-scale multi-agent systems for Siemens customers and business units. I also help shape the company’s physical AI strategy and co-initiate industry partnerships on industrial foundation models. Alongside, I do research as an associated researcher at the ETH Agentic Systems Lab.
I hold a PhD in applied AI from ETH Zurich and a master’s in electrical engineering from RWTH Aachen. Further, I was a visiting researcher at Yale, collaborated with research teams at Google and UC Berkeley, worked with SAP, Mercedes-Benz, Bosch and the Swiss Federal Office of Energy, and founded an augmented reality startup. Along the way I’ve worked on AI for time series, computer vision, neural architecture search and logic optimization.
Check out my personal website where I collect what I’ve built while exploring and creating in all directions. If you’d like to collaborate or share an idea, get in touch.
General links:
- 👨💻 Personal Website
- 📄 Google Scholar
- 🖇 ORCID
- 📧 Contact
Links to some of my work:
| Publication | Paper | Code |
|---|---|---|
| Brudermueller, T., Potthoff, U., Fleisch, E., Wortmann, F., Staake, T. (2025). Estimation of energy efficiency of heat pumps in residential buildings using real operation data. Nature Communications, 16(1), 2834. | Link | |
| Brudermueller, T., Fleisch, E., González Vayá, M., Staake, T. (2025). HEAPO – An Open Dataset for Heat Pump Optimization with Smart Electricity Meter Data and On-Site Inspection Protocols. arXiv preprint arXiv:2503.16993. | Link | Link |
| Brudermueller, T., & Kreft, M. (2023). Smart Meter Data Analytics: Practical Use-Cases and Best Practices of Machine Learning Applications for Energy Data in the Residential Sector. Workshop Tackling Climate Change with Machine Learning, International Conference on Learning Representations (ICLR). | Link | Link |
| Brudermueller, T., Kreft, M., Fleisch, E., & Staake, T. (2023). Large-scale monitoring of residential heat pump cycling using smart meter data. Applied Energy, 350, 121734. | Link | Link |
| Brudermueller, T., Breer, F., & Staake, T. (2023). Disaggregation of Heat Pump Load Profiles From Low-Resolution Smart Meter Data. In Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '23). Association for Computing Machinery, New York, NY, USA, 228–231. | Link | Link |
| Brudermueller, T., Wirth, F., Weigert, A., & Staake, T. (2022). Automatic differentiation of variable and fixed speed heat pumps with smart meter data. In 2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) (pp. 412-418). IEEE. | Link | Link |
| Brudermueller, T., Shung, D. L., Stanley, A. J., Stegmaier, J., & Krishnaswamy, S. (2020). Making logic learnable with neural networks. arXiv preprint arXiv:2002.03847. | Link | Link |
| Kreft, M., Brudermueller, T., Fleisch, E., & Staake, T. (2024). Predictability of electric vehicle charging: explaining extensive user behavior-specific heterogeneity. Applied Energy, 370, 123544. | Link | Link |