PhD Position in Test-Time Adaptation and Agentic AI
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 15 May 2026 or later. You can submit your application via the link under 'how to apply'.
TitlePhD Position in Test-Time Adaptation and Agentic AI
Research area and project description
We invite applications for a fully funded PhD position at Aarhus University in the Department of Electrical and Computer Engineering, within the newly established A3 Lab – Adaptive & Agentic AI.
The PhD project focuses on developing robust and reliable machine learning systems that can adapt at test time under real-world distribution shifts. Modern foundation models (e.g. vision–language and multimodal models) often perform well during training but degrade after deployment due to changes in data, environment, sensors, or user behaviour.The goal of this PhD is to design methods that allow such models to safely adapt after deployment while maintaining reliability and efficiency.
A central research direction is test-time adaptation for multimodal foundation models, combined with agentic decision-making mechanisms that determine when, how, and whether adaptation should occur. This includes developing adaptive systems that can monitor their own reliability, detect distribution shifts, select trustworthy samples, and apply lightweight updates or fallback strategies when appropriate.The project will also explore feedback-driven and reward-based adaptation, uncertainty estimation, calibration, and out-of-distribution detection.
The PhD candidate will work on novel algorithms, theoretical insights, and large-scale empirical evaluations, with a strong emphasis on reproducibility and real-world relevance. The position offers opportunities to collaborate internationally and to publish research at leading machine learning and computer vision venues such as NeurIPS, ICML, ICLR, CVPR, and ECCV.
The successful candidate will join a dynamic research environment at Aarhus University and will be encouraged to contribute to open-source software and interdisciplinary collaborations.
Application: Please submit (1) a 1-page statement of Interest describing your background, research interests, and fit for the project, (2) a CV (including publication list, if any), and (3) academic transcripts and diplomas.- Project description. For technical reasons, you must upload a project description. Please simply copy the project description above and upload it as a PDF in the application.
Qualifications and specific competences
Applicants must hold a relevant Master’s degree (120 ECTS) in Electrical Engineering, Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a closely related field. Applicants who are close to completing their Master’s degree at the time of application may also be considered, provided the degree is completed before enrollment.
A strong background in machine learning and/or computer vision is required, along with solid programming skills in Python and experience with deep learning frameworks (e.g. PyTorch). Prior research experience, such as a Master’s thesis, publications, or substantial research projects, is considered an advantage.
Place of employment and place of work
The place of employment is Aarhus University, and the place of work is Department of Electrical and Computer Engineering (ECE), Faculty of Technical Sciences, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark.
Contacts
Applicants seeking further information regarding the PhD position are invited to contact:
- Associate Professor Behzad Bozorgtabar, behzad@ece.au.dk (main supervisor)
For information about application requirements and mandatory attachments, please see our application guide. If answers cannot be found there, please contact:
- admission.gradschool.tech@au.dk
Please follow this link to submit your application.
Application deadline is 26 February 2026 at 23:59 CET.
Preferred starting date is 15 May 2026.
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.
All interested candidates are encouraged to apply, regardless of their personal background. Salary and terms of employment are in accordance with applicable collective agreement.
Please note in your application that you found the job at Jobindex