Post Graduate Research (PhD) Studentship in Distributed Algorithms in collaboration with CERN Geneva
College of Engineering and Technology, Department of Electronics, Computing & Mathematics
We are seeking to recruit a full time Traditional Route PhD Student to carry out high quality research and development in Distributed Algorithms, particularly producing state of the art data science and deep learning algorithms that can make use of Cloud/Grid and High Performance computing platforms to support High Speed Big Data Analytics. This studentship will investigate state of the art data science algorithms for High Energy Physics Analysis (both online and offline analytics). The candidate will implement and demonstrate these algorithms for functionality, accuracy, performance and scalability within a distributed computing environment. These algorithms will work in collaboration with existing and new resource management, scheduling and workload management models to support High speed Big Data Analytics.
Applicants must hold a Master degree in computer science, mathematics or a related discipline and should have a strong software development expertise in distributed algorithms, distributed systems or high performance computing.
Applicants with prior experience in Cloud and Grid Computing, and with strong distributed systems, data analytics algorithms, machine learning and programming skills, are strongly encouraged to apply.
The algorithms will need to support existing Grid Middleware in CERN, particularly Alien. Alien is a lightweight Open Source Grid Framework built around other Open Source components using the combination of Web Services and Distributed Agent Model. It started within the ALICE Off-line Project at CERN and constitutes the production environment for simulation, reconstruction, and analysis of physics data of the ALICE Experiment. The challenge is to define an offering to the CERN scientists that can enable them to exploit state of the art data science and deep learning algorithms and approaches for big data analytics.
A team at the University of Derby is working closely with CERN (www.cern.ch). The results of the research will be immediately put into practice making a difference to the researchers and benefiting the scientific community.
- Research and develop distributed algorithms that can process large sets (petabytes) of High Energy Physics data.
- Investigate and implement data science and deep learning algorithms that can aid in the physicists in their large scale analysis studies.
- Research & develop approaches that can run these algorithms in HPC and Cloud/Grid platforms
- Produce scalable algorithms and optimize their performance for analysis of Big data
- Drive the collaboration with CERN Geneva, our scientific partner.
- Work in an international team to quickly understand requirements and produce solutions.
- Provide a high level of integrity and commitment towards the project.
- Produce excellent research outputs and high quality publications.
The start date is December 2016 or soon thereafter. If appointed, you’ll receive £14,500 per annum (p.a.) for three years. There is also - subject to satisfactory progress – an extra £1,000 p.a. for professional development purposes. Fees will be covered at a UK/EU level. Funding will be awarded for a period of up to three years subject to satisfactory progress. This is a full time Traditional Route PhD studentship for UK/EU candidates only.
Deadline for applications: Friday 18 November 2016
Informal enquiries may be addressed to Professor Ashiq Anjum, email@example.com
For details of how to apply, please see:
- Applications must be made using the RD02 form (MPhil/PhD by Thesis Application Form) which can be found in the link above.
- When submitting your application, please include the reference code ALG16 in the title of your email.
- Complete applications should be forwarded to Stuart Wain at firstname.lastname@example.org
Interviews to be held on 2 December 2016. If you have not been contacted by the interview date please assume that on this occasion you have not been shortlisted for interview.