Research Assistant (078818)

Applications are invited for the position of Research Assistant in the Department of Computer Science to work in the area of complex networks and more specifically, on machine learning, discovery/prediction and decision control. The position is associated with the Real-Time Flow project and involves a range of activities to conduct research into controllability, resilience and re-configuration of transport networks, based on real-time movement data of people and goods in a city.

The Real-Time Flow project is funded by a grant from the EIT Digital and includes industrial partners Amey (lead), Ferrovial and Emu Analytics. 

The aim of this project is to develop new technologies for better managing the logistics of every day in urban environments, including the ‘last-mile’ delivery. You will be working as part of a team of researchers, PhD students and academic staff to deliver this project, which is initially funded for 12 months. As a Research Fellow on this project, you will be expected to:

develop machine learning techniques and predictive software to support evaluation of a data-rich intelligent platform within the specific domain of activity. conduct high-quality research in data pre-processing, machine learning and discovery and explore the implications on network adaptation and controllability

You will also be expected to support the other research activities within the team, and to support the PhD students as required.

You will have a good honours degree in Computer Science or in a relevant discipline, ideally including evidence of mathematics ability and programing skills. Practical research expertise in machine learning and complexity is desirable. The initial contracts will be for 2 months and we anticipate a 12 month extension will be offered based on performance/project approval.

Informal academic enquiries may be made to Dr Sotiris Moschoyiannis in the Department of Computer Science at s.moschoyiannis@surrey.ac.uk.

Please apply online through the button below.

Closing Date: 18 Oct 2018
Category: Research & Teaching