Research Associate in Optimisation and Mapping of Generative AI models on GPUs and on the cloud

Location: South Kensington Campus

About the role:

Applications are invited for the above post to work with Professor Christos Bouganis and his team at Imperial College London for a project funded by the Commission of the European Communities.

The successful candidate will be integral to delivering on the project called “Human-centred generative Ai fraMework for culturaL industriEs’ digital transiTion" - HAMLET”, https://hamlet-project.eu. Its mission is to make Generative AI benefits accessible to entities of all sizes, in order to foster a sustainable digital transition. The team at Imperial focuses on the DNN model optimization and deployment in an attempt to democratize the use of generarative AI by reducing the cost of its use through a reduction on their computational requirements as well as to further enable its use by reducing the latency of their execution in a collaborative environment in an edge-cloud computing setting.

What you would be doing:

The successful candidate will research and develop methodologies that optimise the deployment of DNN models, and more specifically models in the space of generative AI, by considering:

1. the opportunities provided from the synergy of local and cloud computing,
2. the robustness of the targeted DNN models by pushing further the model compression due to the specific application domain,
3. the opportunities raised by modern device architectures and their native support for DNN loads.

What we are looking for:

The successful candidate:

• Will have a PhD (or be very near completion or equivalent) in engineering, mathematics, physics, or a related topic.
• Experience with DNN theory and the mapping of DNN models on a device.
• Experience in optimizing DNN models for deployment including pruning and quantisation.
• Experience with Generative AI
• Experience with programming in CUDA.

What we can offer you:

• An opportunity to play a key role in a multidisciplinary team driving innovation in the deployment of deep neural network (DNN) models across a continuum of edge-to-cloud computing platforms.
• Close interaction with the highly motivated and diverse team of Prof. Bouganis all working on researching hardware architectures and algortihms for the acceleration of Deep Neural Networks (https://www.imperial.ac.uk/intelligent-digital-systems/)

Further Information

Professor Bouganis’ team is based at Imperial College’s South Kensington campus in the heart of London, UK. Professor Bouganis is an expert in the design of intelligent digital systems and leads the iDSL group at Imperial College (https://www.imperial.ac.uk/idsl), with a focus on the theory and practice of reconfigurable computing and design automation, mainly targeting the domains of Machine Learning, Computer Vision and Robotics. 

This full-time, in-person postdoctoral position is based at Imperial College’s South Kensington campus in London, UK and is funded for up to 24 months, starting in September/October 2025.

If you require any further details on the role please contact:

Christos Bouganis christos-savvas.bouganis@imperial.ac.uk.

If you encounter any technical issues while applying online, please don't hesitate to email us at support.jobs@imperial.ac.uk. We're here to help.

Advert information