Postdoctoral Research Associate in Applied Statistics and Computational Ima

at  Heriot Watt University

Directorate: School of Engineering & Physical Sciences
Salary: Grade 7 (£36,924-£46,485)
Contract Type: Full Time (1FTE), Fixed Term (18 Months)
Rewards and Benefits: 33 days annual leave, plus 9 buildings closed days for all full time staff (Part time workers should pro rata this by their FTE). Use our total rewards calculator: https://www.hw.ac.uk/about/work/total-rewards-calculator.htm to see the value of benefits provided by Heriot-Watt University

DETAILED DESCRIPTION

This project is part of the new UK Hub in Quantum Sensing Imaging and Timing (QuSIT), that stands as an international centre of excellence for research and innovation, providing thought leadership, coordination and translation to impact across the quantum landscape in the UK and beyond. QuSIT builds upon a decade of government, institutional and industry investment, unifying expertise from two existing internationally leading Hubs in QT Imaging (QuantIC) and Sensing and Timing, maintaining coherence within the UK landscape, bringing together industry, government, and the international community. This Hub is a crucial vector for the delivery of the National Quantum Strategy, enhancing UK prosperity and national security.
This position aims at addressing computational challenges associated with data acquisition and information extraction from complex sensors and sensor networks. Crucially, uncertainty management and quantification tools are need during the development of new imaging and sensing systems. With the rapid deployment of data-driven methods, repliable uncertainty quantification remains a big challenge that requires the development of principled, mathematical tools. Such tools need to be able to handle a variety of working environments (e.g., dynamic environments), input data (from traditional frame-based data to non-traditional, e.g., event data) and network structures (for sensor networks). In this project, we will investigate Bayesian deep learning approaches to training models under uncertainty for several sensing, imaging and timing applications.

In this project, we will:

• Develop Bayesian deep learning methods for event-based data, including single-photon detections and neuromorphic camera data.
• Investigate Bayesian graph neural networks for complex sensor networks such as those involved in brain imaging
• Develop and test data-driven methods for image and video processing for microendoscopy.

• Develop suitable algorithmic methods for live and real-time analysis of synchronous and asynchronous data.
• Write research reports and publications. Analyse and interpret the results of own research and generate original ideas bases on outcomes. Prepare proposals and applications to external bodies, e.g. for funding purposes. Use initiative and creativity to identify areas for research, develop new research methods and extend the research portfolio.
• Build internal contacts and participate in internal networks for the exchange of information and to form relationships for future collaboration. Work with academic colleagues on areas of shared research interest and contribute to collaborative decision making. Join external networks to share information and identify potential sources of funds.
• Provide guidance as required to support staff, research students and any other students who may be assisting with the research.
• Contribute, under supervision, to the planning of research projects, including the development of new grant/contract proposals. Make internal and external contacts to develop knowledge and understanding and form relationships for future collaboration.We are looking for a creative and highly motivated researcher willing to work as part of a multidisciplinary team.The ideal candidate will have a strong theoretical understanding and an experimental background in one or more of the following fields: Statistical signal/image processing, deep learning, machine learning, neuromorphic computing
• Good communication skills and an appropriate publication record are essential.
• Solid knowledge of Python and C++ is essential.
• General tasks will involve scientific research; analysis and interpretation of data; communication with other investigators involved in this collaborative project; preparation of scientific papers
• The successful candidate will be expected to conduct and lead their own experiments whilst also supervising the activities of junior group members and PhD students
• Responsibilities will also include assistance in the day-to-day maintenance of the experimental facilities, liaising with companies and external collaborators
• The successful candidate is also expected to be involved in our outreach activities, with roles that can be tuned to the specific preferences of the candidate but will involve for example interviews, talks for the general public and preparation of experimental demonstrators.
  Please note that this job description is not exhaustive, and the role holder may be required to undertake other relevant duties commensurate with the grading of the post and its general responsibilities. Activities may be subject to amendment over time as the role develops and/or priorities and requirements evolve.