Senior Research Associate in Machine Learning and Crowdsourcing for Disaster Relief (A2767)

The Physics Department, University of Lancaster is seeking an enthusiastic and creative scientist to work on the combination of machine learning and crowdsourcing for disaster relief and resilience applications. Accurate change detection and data labelling in time-sensitive applications such as disaster relief is critical to many applications of algorithms. This project explores the combination of machine learning with human data labels via the crowdsourcing platform Zooniverse. We have a well-established project organisation to deploy projects in partnership with disaster response and relief organisations, and funding from the STFC to employ novel techniques to combine human and machine classifications in this context.

You will work in the Physics department within the research group headed by Dr Brooke Simmons, and collaborate with colleagues in multiple disciplines within the university and externally, including partners at the University of Oxford and the response and resilience organisation Rescue Global. 

You must have at least a PhD in Computer Science, Physics or a related field and have expertise in applying AI/ML algorithms, preferably to change-detection and/or related applications. A good record of refereed research outputs is also preferred. You are expected to successfully work as part of a team with good inter-personal skills. 

Lancaster University Physics Department is strongly committed to fostering diversity within its community as a source of excellence, cultural enrichment, and social strength. We welcome those who would contribute to the further diversification of our department.

This is a fixed term appointment for 12 months.

Applicants may find some helpful information on local amenities here:

http://www.physics.lancs.ac.uk/jobs/amenities/

Informal enquiries can be made to Dr Brooke Simmons (b.simmons@lancaster.ac.uk).

We welcome applications from people in underrepresented groups.

Closing Date: 09 Aug 2019
Category: Research