Research Associate in Analogue AI Accelerators

About us

Recently re-founded, the Department of Engineering is rapidly expanding into a world-class research and teaching department. Research currently focuses on information processing systems, robotics, telecommunications and biomedical engineering, but we are looking to establish new research themes.  

The vision for King’s engineering is to develop discovery, innovation and leadership in engineering education and research.

The central role played by engineering in our lives extends far beyond clichéd associations with construction, heavy machinery, manufacturing and mineral extraction. Today, some of the greatest advances in engineering are being made in fields such as robotics, biomedicine and IT – areas in which King’s has particular strength.

This post will be affiliated with the newly established Centre for Intelligent Information Processing Systems within the department. 

About the role

We are seeking a highly motivated and conscientious post-doctoral researcher to join a very collaborative, interdisciplinary, and friendly research group at King's College London led by Professor Bipin Rajendran. 

The group at King's is part of a consortium developing multiprocessor systems-on-chip with advanced nanoscale in-memory neural processing units that are funded by the Horizon Europe Programme. The consortium team will develop an advanced Multi-Processor System on Chip prototype in FD-SOI 28nm CMOS technology that tightly integrates an Analog In-Memory Computing (AIMC) unit based on embedded phase-change memory technology. As part of this project, you will have the opportunity to collaborate with world-leading researchers from industries (including IBM Research and ST Microelectronics) and universities in Europe.

You will contribute to the architecture and design of the neural processing unit that comprises one or more AIMC tiles. The project will also involve the use of a Pytorch-based simulation environment for network optimisation that is incorporating the statistical behavioural features of AIMC hardware. You will also further develop hardware-aware training methodologies optimized for inference with the architecture and collaborate with project partners involved in the experimental demonstrations of various Machine Learning use cases in the new hardware. You will also have the opportunity to mentor PhD and MSc students working in Professor Rajendran's group.

This is a full time post, and you will be offered a fixed term contract until 28 Feb 2026.

About you

To be successful in this role, we are looking for candidates to have the following skills and experience:

Essential criteria

1. PhD awarded (or near completion) in Electrical or Computer Engineering
2. Knowledge about Deep Learning algorithms, models, and their optimization techniques
3. Knowledge of at least one of TensorFlow, PyTorch, etc.
4. Effective communication (oral and written) skills, ability to write research reports and papers in style accessible to academic audiences
5. Experience with developing and optimizing deep learning models
6. Track record of high-quality research publications in peer reviewed conferences and/or journals.
7. Ability to work independently and as part of a team on research programmes

Desirable criteria

1. Experience with hardware aware optimization of state-of-the-art machine learning models.

Full details of the role and the skills, knowledge and experience required can be found in the Job Description document, via the above ‘Apply’ button. This document will provide information of what criteria will be assessed at each stage of the recruitment process.

Further Information

We pride ourselves on being inclusive and welcoming. We embrace diversity and want everyone to feel that they belong and are connected to others in our community.

Interviews are due to be held in July 2024

Closing date: 27/06/2024

Advert information