The goal of this project is to develop and evaluate machine-learning campaigns as well as big data architectures that continuously analyze software-defined infrastructures, their qualities, code smells, qualities as well as runtime adaptation possibilities in the scope of DevOps continuous evolution. The Post-Docs will contribute with an advisory, research dissemination, teaching, and mentoring role during the exploration and improvement of state-of-the-art machine- and deep-learning approaches and develop prototypes for the afore-mentioned analysis in the context of sound Empirical Software and Data Engineering research.
The to-be-developed approaches and algorithms will contribute to high-relevance/high-impact research in the context of two EU H2020 Projects focused on the afore-mentioned topics and most notably, serverless computing. More specifically, one of the two Post-Docs will be actively involved in the EU H2020 RADON project with a co-supervisory role over a Ph.D. student; the post-doc will aid in the envisioning, prototyping, evaluation and dissemination of Defect Prediction approaches specifically designed for infrastructure code. In parallel, the second post-doc will be involved in the EU H2020 SODALITE project with a co-supervisory role over a Ph.D. student; together they will help envision, prototype, and evaluate design patterns and code smells detection facilities for infrastructure code as well as automated code refactoring mechanisms for smart service orchestration.
The applications will also be developed by industrial commercial partners in the scope of the afore-mentioned H2020 actions and will include additional functionality providing the user with further industrial data and information from the value-generating industrial context.
The project is a collaboration of the Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch (campus Mariënburg), Tilburg University (TiU), Eindhoven University of Technology (TU/e) and the commercial, industrial and academic partners part of the actions above.
ProfileThe research will be conducted under supervision of Prof. Dr. Willem-Jan van den Heuvel and Dr. Damian A. Tamburri. The students are expected to deliver both long-term results (understanding of machine learning in quality evaluation of software-defined infrastructures) and mid-term results (algorithms, approaches, high-impact/high-relevance papers, and best practices).
The successful candidate is expected to:
- Perform scientific research in the domain described;
- Develop software that implements the algorithms described;
- Present results at (international) conferences;
- Publish results in scientific journals;
Participate in activities of the group, mainly in 's-Hertogenbosch but sometimes also in Eindhoven or Tilburg or at one of the commercial partners in several locations in Europe.