Bayes Centre Huawei Fellow

We are seeking a Bayes Centre Huawei Fellow to work on an exciting project in the field of edge LLM systems.  The project consists of three work packages: (1) evaluating LLMs on edge devices by analyzing accuracy, latency, and energy efficiency, (2) developing novel sparsity and low-rank methods, including KV cache compression and sparse MLP activations, and (3) releasing the work as open-source and publishing findings. The goal is to make LLMs more accessible and efficient for edge applications

The Opportunity

This post is full-time (35 hours per week), fixed-term for one year.  We are open to considering part-time or flexible working patterns.  We are also open to considering requests for hybrid working (on a non-contractual basis) that combines a mix of remote and regular on-campus working. 

Your skills and attributes for success

• A PhD or in final stage (awaiting viva or completing corrections) in computer science or a related discipline, with excellent technical expertise and experience in the areas of Data Science and Informatics as defined by the Bayes Centre and Huawei.
• Strong background and expertise in LLMs, edge systems, deep learning algorithms and computer systems.
• Experience and evidence of effective independent research work within an interdisciplinary team. More broadly, demonstrated ability to lead, design and complete research projects, to solve problems independently and make original contributions to research.
• Excellence in written and oral communication, analytical, planning, and time management skills.

Advert information