PhD in Computer Science (Infrastructure Virtualisation for e-Science)

The objective of this research is to study how to develop support for specific application types and application areas in schedulers for large-scale systems such as grids and clouds. Different application types, both old (e.g., workflows) and new (e.g., data-mining at unprecedented scales), may want to take advantage of the capabilities of evolving large-scale computing infrastructures, such as (inter-operating, federated) grids and clouds with their heterogeneous hardware (processor types) and high-speed networks. No single scheduler can incorporate support for all imaginable types of applications for all types of computing infrastructures. Therefore, there is a need to design and build application-support modules in schedulers of large-scale distributed systems.

More specifically, the goal is to develop support in the KOALA scheduler for specific application types and for applications in specific application areas (e.g., medicine) that are studied in other projects in COMMIT. For this purpose, the current KOALA scheduler has to be extended with application-support modules for these application types and application areas in such a way that users do not have to deal with myriad details of the underlying systems, but can concentrate on application design, and that applications can run (energy-)efficiently. This research will be carried out in collaboration with other COMMIT projects.

www.pds.ewi.tudelft.nl
www.pds.ewi.tudelft.nl/epema
www.st.ewi.tudelft.nl/koala
www.cs.vu.nl/das4

Applicants must have a Master's degree in computer science with an emphasis on computer systems and performance analysis, and preferably on experimental computer science.

TU Delft offers an attractive benefits package, including a flexible work week, free high-speed Internet access from home (with a contract of two years or longer), and the option of assembling a customised compensation and benefits package (the 'IKA'). Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.

For more information about this position or to apply, please contact Dick Epema, phone: +31 (0)15-2783853, e-mail: d.h.j.epema@tudelft.nl. To apply, please send a detailed CV, transcripts of your BSc and MSc results, and a copy of your MSc thesis along with a letter of application by April 1, 2012, to Prof. Epema. You may submit your application by e-mail to d.h.j.epema@tudelft.nl or by post to Mekelweg 4, 2628 CD Delft, The Netherlands.

When applying for this position, please refer to vacancy number EWI2011-19.

Delft University of Technology (TU Delft) is a multifaceted institution offering education and carrying out research in the technical sciences at an internationally recognised level. Education, research and design are strongly oriented towards applicability. TU Delft develops technologies for future generations, focusing on sustainability, safety and economic vitality. At TU Delft you will work in an environment where technical sciences and society converge. TU Delft comprises eight faculties, unique laboratories, research institutes and schools.

The Department of Software Technology comprises the EEMCS Faculty research groups working on core computer science topics. The department is responsible for a large part of the curriculum of the BSc and MSc programmes in Computer Science. The department’s research mission is to perform excellent research at an internationally recognised level in the design, construction and analysis of complex, concurrent and co-operative computer and information systems. Inspiration for the research topics is derived largely from technical ICT problems in industry and society. The department currently consists of the following groups: Parallel and Distributed Systems, Software Engineering, Embedded Software, Algorithms, Web Information Systems, and Computer Engineering.


In the PDS group in Delft, two staff members and three PhD students are currently active in the area of resource management and scheduling in grids and clouds, with the research centering around the KOALA grid scheduler, developed in the PDS group in Delft. The research in the PDS group is experimental in nature, with a strong emphasis on designing, implementing, deploying, and analysing prototypes in real systems.

Over the past decade, the PDS group has built up a very strong portfolio of research in resource management and scheduling in grids and clouds, with four completed PhD theses and a large set of papers in the top conferences and journals publishing in this field. TUD participates in the DAS4 project, and with the DAS4 has an excellent grid and cloud experimental facility.

Dick Epema
+31 (0)15-2783853
d.h.j.epema@tudelft.nl

Technische Universiteit Delft