SPRING is a MSCA Doctoral Network under the Horizon Europe framework. It focuses on the resilience of future large-scale critical infrastructures that are deeply interconnected, cyber-physical, and exposed to evolving threats such as extreme weather, cascading failures, cyber-attacks and human error.
In this realm, two PhD positions will be opened at Bielefeld University targeting opportunities and challenges of AI technologies in this context. One position (DC1 Physics-informed adversarial robustness of network models) centers around the investigation of adversarial attacks on smart components in critical infrastructure. A special emphasis will be put on the questions which attacks can occur naturally in this context and how do defend those, using concepts from physics-informed machine learning and its transfer to physics-informed generative models which enable a robustification of data-driven components in this domain. The other position (DC5 Explaining complex drift phenomena in networked data) deals with the identification of anomalies which manifest itself in distributional changes and its explanation and remedy based on novel technologies from explainable AI which can consider complex interactions as occur in complex systems. These methods should be applied for the identification of emerging risks which are caused by dissonance of several network components in critical infrastructure.
Your Tasks
1. development and implementation of machine learning technologies which deal with these challenges, 40 %
2. implementation and evaluation in benchmark scenarios (e. g. water distribution systems, energy systems, transportation), 20 %
3. application in cooperation with secondment partners of the DN, 20 %
4. publication of results in high quality venues, 10 %
5. participation in DN events, such as summer schools, 5 %
6. cooperation with international project partners, 5 %
An important component of the DN is secondments to project partners in industry and research. This offers the opportunity to gain a deeper insight into methods used and a broader view of applications.
Since the position is financed by third-party funds, the following must be observed according to the requirements of the third-party funder: In line with the objective of DNs to strengthen international cooperation, applicants may not have been resident and/or active in Germany for more than twelve months during the last three years at the time of recruitment. Furthermore, applicants must not yet have obtained a doctoral degree. Due to the funding regulations, the position is available on a full-time basis only.
Employment is conducive to academic qualification, and opportunities for academic (further) qualification are provided. Your Profile We expect
7. relevant scientific university degree in computer sciences, engineering, mathematics, physics or equivalent
8. excellent programming skills, in particular Python
9. knowledge of machine learning
10. experience in deep learning
11. advanced skills in mathematical modeling
12. English, fluent in spoken and written language
13. independent, conscientious and diligent working style
14. cooperative and team-oriented approach to work
15. openness to application-oriented questions in an industrial context
Preferred experience and skills
16. interest in interdisciplinary work
We offer
17. salary according to Remuneration level 13 TV-L (min. EUR 4,
18. fixed-term (3 years) (§ 2 (1) sentence 1 of the WissZeitVG; in accordance with the provisions of the WissZeitVG and the Agreement on Satisfactory Conditions of Employment, the length of contract may differ in individual cases)
19. fulltime
20. internal and external training opportunities
21. variety of health, consulting and prevention services
22. reconcilability of family and work
23. 30 days holiday and additional days off on ;and
24. fundamental possibility of mobile working
25. supplementary company pension
26. collegial working environment
27. open and pleasant working atmosphere
28. various offers (canteen, cafeteria, restaurants, Uni-Shop, ATM, etc.)
Application Procedure
We are looking forward to receiving your application. To apply, please preferably use our online form via the application button below.
application deadline: Contact
Prof'in Dr. Barbara Hammer
+49 521 106-12115
Postal Address
Universität Bielefeld
Citec - AG Maschinelles Lernen
Prof'in Dr. Barbara Hammer
Postfach 10 01 31
33501 Bielefeld