Explainable Industrial Condition Monitoring with Federated Learning

About us We are the Chair for Application and Middleware Systems at the Technical University of Munich. Our aim is to perform high-quality research in the area of distributed systems, middleware and data management. Requirements Master’s degree in computer science with very good results Interest on topics around the area of explainability in AI, data privacy and machine learning Previous knowledge in distributed systems and machine learning is desired Hand-on experience with large-scale machine learning frameworks (PyTorch, TensorFlow, etc.) is a plus Experience with DevOps tools (Ansible, GitLab) and Linux distributions is desired Interest in the development of software systems, very good knowledge and skills in programming with standard programming languages such as Python Excellent command of English Very good writing skills High engagement, high motivation, pro-active communication skills, and high social skills Your tasks Due to the increasing relevance of automation, Industry 4.0 has moved into a market-ready format. In order to operate the increasingly complex industrial processes in an economically feasible manner, continuous condition monitoring helps to cut costs. However, the increasing amount of data generated at the edge of the network and the importance of data privacy are challenging central cloud approaches. Another important aspect of Industry 4.0 is to increase the explainability of AI algorithms for industrial machinery and processes in order to comply with safety standards and to get repeatable results for testing control systems. The machine learning process is shifted from the cloud to edge devices to use locally available computing resources in a federated fashion. To solve these issues, we are starting a research project that aims at developing new systems and algorithms to increase the traceability and accuracy of AI models, to build distributed privacy preserving AI pipelines (using federated learning) and to improve cybersecurity by analyzing attack scenarios and building fingerprinting methods for data sovereignty. To perform this exciting research, we are looking for a highly motivated student who has recently finished his/her Master’s degree in computer science. This position comes with the opportunity to obtain a PhD. We offer You work in a highly innovative environment. Technical supervision at one of the leading universities of Germany. Employment as a research associate (TVL-E13) in a fulltime position (fixed-term contract). Funds for travel and student helpers (HiWis) is available from the project. Disabled persons will be preferred at the same level of suitability to the position. The Technical University of Munich seeks to increase the proportion of women. Hence, we explicitly encourage women to apply to this position. We will consider all incoming applications until the position is filled. Application We are looking forward to your application. Please send your CV, a short motivation letter, a list of publications if applicable (also blog posts and software projects), and full transcripts of records of your B.Sc. and M.Sc. studies, all combined in one single PDF document, to ruben.mayer@tum.de. Alternatively, you can send your application by mail. Technical University of Munich Chair for Application and Middleware Systems Boltzmannstrasse 3, 85478 Garching, Germany Tel. +49 (89) 289 – 18486 ruben.mayer@tum.de http://www.i13.in.tum.de Data Protection Information: When you apply for a position with the Technical University of Munich (TUM), you are submitting personal information. With regard to personal information, please take note of the Datenschutzhinweise gemäß Art. 13 Datenschutz-Grundverordnung (DSGVO) zur Erhebung und Verarbeitung von personenbezogenen Daten im Rahmen Ihrer Bewerbung. (data protection information on collecting and processing personal data contained in your application in accordance with Art. 13 of the General Data Protection Regulation (GDPR)). By submitting your application, you confirm that you have acknowledged the above data protection information of TUM.