Research Associate in Neuromorphic Engineering - Manchester, United Kingdom - The University of Manchester

Description

The successful applicant will join the University of Manchester as part of the EU-funded research project CONVOLVE: Low-Power Processing at the Edge. The project brings together 18 partners from across Europe to investigate hardware and software design to accelerate the development of very low power hardware for intelligent processing. Aspects of this work addressed by the consortium include: the development of hardware accelerators to deliver energy efficient performance on neural network and machine learning tasks; new computation methods and learning algorithms for both artificial and spiking neural networks; advanced compiler techniques to make use of the new hardware accelerators; and system design tools to allow the rapid construction and tuning of parameterized SoC solutions for a set of industry-sponsored target applications.

Manchester has a long and distinguished track record in the research and teaching of core Computer Science, and across interfaces to adjacent disciplines. Founded upon the pioneering work of Williams, Kilburn and Turing, the Department was the first academic Department of Computer Science in the UK and one of the first to run an undergraduate programme. The research strength of the school is reflected in consistently strong returns in UK research assessment exercises (5* in RAE 2000, 2nd in Research Power in RAE 2008, and ranked equal 1st for research environment in REF2014 and REF2021).

The Manchester team's contribution to the CONVOLVE project is in two work packages: one is concerned the theory of neural networks (both artificial and spiking), focusing on reduced computational cost, continuous learning and compute models using spikes; the second work package focuses on hardware acceleration of key functions for edge processing, tied to a central RISC-V core. Working with industry-based partners who each have a target application, we are working to demonstrate the benefits of new IP through implementation of neural network pipelines on FPGA.

The successful candidate will be responsible for continuing our development and testing of neural network accelerators for both ANNs and SNNs, as well as their mapping to a Xilinx UltraScale+ FPGA.

What you will get in return:

• Fantastic market leading Pension scheme
• Excellent employee health and wellbeing services including an Employee Assistance Programme
• Exceptional starting annual leave entitlement, plus bank holidays
• Additional paid closure over the Christmas period
• Local and national discounts at a range of major retailers

The Department of Computer Science is strongly committed to promoting equality and diversity, including the Athena SWAN Charter for gender equality in higher education. The School holds a Bronze Award which recognises their good practice in relation to gender; including flexible working arrangements, family-friendly policies, and support to allow staff to achieve a good work-life balance.

We particularly welcome applications from women and other under-represented groups for this post. Appointment will always be made on merit. For further information, please visit

The University will actively foster a culture of inclusion and diversity and will seek to achieve true equality of opportunity for all members of its community.

Our University is positive about flexible working you can find out more here

Hybrid working arrangements may be considered.

Please note that we are unable to respond to enquiries, accept CVs or applications from Recruitment Agencies.

Any recruitment enquiries from recruitment agencies should be directed to

Any CV's submitted by a recruitment agency will be considered a gift.

Enquiries about the vacancy, shortlisting and interviews:

Name: James Garside

Email:

General enquiries:

Email:

Technical support:

This vacancy will close for applications at midnight on the closing date.

Please see the link below for the Further Particulars document which contains the person specification criteria.