The Research Division Distributed Systems, E194-02, Institute of Information Systems Engineering, TU Wien, is offering a part-time position (30 hours/week) for a prae-doc project assistant for 36 months. The estimated starting date is January 1, 2027. Entry level salary as a prae-doc project researcher is covered by the Austrian Collective Agreement for university staff and is € 2.832,08 per month gross, 14x per year.
The Project:
Critical infrastructures (i.e., energy distribution and industrial production networks) are increasingly exposed to faults, maintenance disruptions, security incidents, and capacity limitations. In the absence of real-time fault detection, prediction, and recovery, these issues demand costly manual intervention, and traditional, centrally-controlled countermeasures are too static and linear to capture the real-time, nonlinear behavior of tightly networked systems. To keep such infrastructures available and reliable, there is an urgent need for autonomic technologies that self-protect and self-heal — detecting, anticipating, and resolving disruptions in a self-organized way while keeping human operators in control of high-level decisions.
This PhD project addresses this challenge through the exploration of decentralized, self-healing and self-learning systems for resilient critical infrastructures. The position is embedded in the Autonomic Resilience Center (ARC), a new academia–industry competence center advancing the science and practice of resilience in dynamic networked systems, within Research Area 2 – Self-Organization for Resilience. The doctoral work is carried out on the project SENA–Self-Healing Networks for Critical Infrastructures, which develops self-healing techniques that autonomically detect, predict, and resolve faults in energy and production networks before service-level objectives are affected. The project establishes decentralized decision-making and adaptive recovery strategies to maintain operational continuity and enhance collaborative learning so that systems evolve toward higher resilience and efficiency. Methods include data analysis, machine learning, active inference, bioinspired algorithms, and temporal-graph models with causal inference for workload allocation and adaptive recovery. A combination of simulation, validation, and proof-of-concept ensures iterative improvement and applicability. The outcome is a suite of algorithms for self-healing behavior (i.e., enabling networks to detect, predict, and resolve disruptions autonomously) validated on real energy and production systems, ideally reducing downtimes and ensuring seamless service continuity.
Your tasks:
- Design and implement novel self-healing techniques (based on active inference) that detect, predict and resolve faults in energy and production networks before service-level objectives are affected.
- Develop novel decentralized decision-making and adaptive recovery strategies (e.g., consensus-based recovery, workload reallocation) based on active inference and temporalgraph models with causal inference.
- Develop collaborative/federated learning schemes so that networks become more resilient and efficient with every disruption they handle.
- Validate your methods in simulations, digital twins and a proof of concept together with industry partners of the ARC consortium.
- Publish your results at top international venues and complete a PhD thesis at TU Wien.
Required qualifications:
- An MSc or comparable degree in computer science, informatics, business informatics, or a closely related discipline, completed with very good grades (at the latest by the starting date).
- Very good knowledge of distributed systems, in particular edge/cloud computing, selfadaptive or autonomic systems and IoT, demonstrated by your Master’s thesis, projects or publications.
- Very good knowledge of machine-learning foundation, including probabilistic/Bayesian methods.
- Strong programming skills (typically Python).
- Very good English skills, written and spoken (at least C1 level).
- In-depth interest in scientific problems and the ability to carry out independent, goal-oriented research.
A plus:
- Knowledge of active inference, causal inference, temporal graphs/graph neural networks, or collaborative/federated learning.
- Experience with reliable and explainable AI.
- Familiarity with bio-inspired algorithms, digital twins, or energy/critical-infrastructure systems.
- Publications or experience in national or international research cooperation.
Personal skills:
- Very good communication and social skills, teamwork, and social and gender competence.
- Contribute actively to cross-project work within the ARC and Research Area 2.
- Willingness to contribute to an interdisciplinary consortium of academic and industry partners, including occasional research stays at partner sites.
We offer:
- A creative environment in one of the most livable cities in the world.
- A young and international team of researchers.
- A range of attractive social benefits (see Benefits).
- A work environment that is well equipped with the newest hardware and software technology.
- Continuing personal and professional education.
- A vibrant consortium spanning universities, research organizations, and industry.
- A high-impact, infrastructure-facing research topic with real-world validation on energy and production systems.
- The possibility to present your research results at international top conferences.
The supervisor will be Prof. Schahram Dustdar. For further information please contact him by email at dustdar@dsg.tuwien.ac.at or contact Dr. Ilir Murturi imurturi@dsg.tuwien.ac.at
Application information:
Applications should be submitted in a single pdf including motivation letter, Curriculum Vitae, certificates, transcripts of records (grades), list of publications and thesis, quoting reference [ARCA2- SENA], by e-mail to Christine Kamper christine.kamper@tuwien.ac.at.
Application Deadline: December 2, 2026
We follow an open, transparent, merit-based, impartial and equitable recruitment process in line with the European Charter for Researchers & Code of Conduct for Recruitment.