Distributed Learning and Inference for Artificial Intelligence of Things - Aarhus, Danmark - Aarhus Universitet, Bygning 5125

Beskrivelse

Applicants are invited for a PhD fellowship/scholarship at Graduate School of Technical Sciences, Aarhus University, Denmark, within the Electrical and Computer Engineering programme. The position is available from 01 September 2024 or later. You can submit your application via the link under 'how to apply'.

Title
Distributed Learning and Inference for Artificial Intelligence of Things

Research area and project description
We invite applications for a PhD position financed by the Horizon Europe project PANDORA and the NordForsk project Nordic University Cooperation on Edge Intelligence (NUEI). The selected candidate will have good opportunities to work, interact, and network with researchers, scientists, and engineers working in European Universities, Research Institutes, and Companies forming its consortium. In addition, the PhD candidate has opportunities to participate in the summer schools and PhD courses in NUEI.

The PhD project aims at developing novel techniques for distributed learning and inference for Transformer-based Deep Learning models in the IoT-Edge-Cloud continuum. Large DNN models with enormous number of model parameters hinder their deployment on a single resource-constrained device. The project aims to design novel learning and inference algorithms to accelerate distributed learning and inference processes, for example, how to leverage model sparsity to reduce inference time and memory footprint, and how to leverage parallelism. In addition, from system perspective the project aims to efficiently manage the trade-off between resource utilisation, and inference accuracy, communication and computation time and energy consumption across the continuum, by adapting to the dynamic changes in the communication networks and data processing environment. We will propose and develop novel algorithms for dynamic workload distribution, load balancing, and energy management, to optimise distributed learning and inferencing in the IoT-Edge-Cloud continuum. The research outcomes will contribute to the advancement of resource-constraint foundation models.
As part of the PhD project, the selected candidate will interact with the collaborators in the two projects, perform knowledge dissemination, e.g., through conference participation and project reporting to present their work, and have the opportunity to participate in activities of the project.

Project description (1⁄2-4 pages). This document should describe your ideas and research plans for this specific project. If you wish to, you can indicate an URL where further information can be found.

Qualifications and specific competences
Applicants to the PhD position must have a:

Master's degree in Computer Engineering, Computer Science, or within a relevant area.

Background on Deep learning is required and experience in transformer or Edge Intelligence, or IoT is a plus.

Strong programming skills, especially Python programming, is required.

Excellent English verbal and written skills.

Be able to work well and communicate expert knowledge in an interdisciplinary team.

Background in video processing, deep learning, or wireless communications is a plus.Place of employment and place of work:
The place of employment is Aarhus University, and the place of work is Helsingforsgade Aarhus N

Contacts
Applicants seeking further information are invited to contact:

Associate Professor Qi Zhang, (main supervisor)

Professor Alexandros Iosifidis, (co-supervisor)
How to apply
Please follow this link to submit your application.

Application deadline is Wednesday 15 May 2024 at 23:59 CEST.

Preferred starting date is 01 September 2024.

For information about application requirements and mandatory attachments, please see our application guide.

Please note:

Only documents received prior to the application deadline will be evaluated. Thus, documents sent after deadline will not be taken into account.

The programme committee may request further information or invite the applicant to attend an interview.

Shortlisting will be used, which means that the evaluation committee only will evaluate the most relevant applications.
Aarhus University's ambition is to be an attractive and inspiring workplace for all and to foster a culture in which each individual has opportunities to thrive, achieve and develop. We view equality and diversity as assets, and we welcome all applicants. All interested candidates are encouraged to apply, regardless of their personal background. Salary and terms of employment are in accordance with applicable collective agreement.