PhD Position in Test-Time Adaptation and Agentic AI (A3 Lab, Aarhus University) Aarhus University in Denmark

A fully funded PhD position is available at the Graduate School of Technical Sciences, Aarhus University, Denmark, within the Electrical and Computer Engineering programme. The successful candidate will join the newly established A3 Lab – Adaptive & Agentic AI, located in the Department of Electrical and Computer Engineering. The research project focuses on developing robust and reliable machine learning systems capable of adapting at test time under real-world distribution shifts. Modern foundation models, including vision–language and multimodal models, often perform well during training but may degrade after deployment due to changes in data, environment, sensors, or user behaviour. This PhD aims to design methods that enable such models to safely adapt after deployment while maintaining reliability and efficiency.

Key research directions include test-time adaptation for multimodal foundation models and agentic decision-making mechanisms that determine when, how, and whether adaptation should occur. The project involves developing adaptive systems that monitor their own reliability, detect distribution shifts, select trustworthy samples, and apply lightweight updates or fallback strategies as needed. Additional areas of exploration include feedback-driven and reward-based adaptation, uncertainty estimation, calibration, and out-of-distribution detection. The 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 for international collaboration and publication at leading machine learning and computer vision venues such as NeurIPS, ICML, ICLR, CVPR, and ECCV. The research environment at Aarhus University is dynamic and encourages contributions to open-source software and interdisciplinary collaborations. The place of employment is Aarhus University, and the place of work is the Department of Electrical and Computer Engineering, Faculty of Technical Sciences, Finlandsgade 22, 8200 Aarhus N, Denmark.

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. Those close to completing their master’s degree may also be considered if 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 such as PyTorch. Prior research experience, including a master’s thesis, publications, or substantial research projects, is considered an advantage.

To apply, submit a 1-page statement of interest describing your background, research interests, and fit for the project, a CV (including publication list, if any), and academic transcripts and diplomas. Applications must be submitted via the provided link, and a PDF copy of the project description should be uploaded. Only documents received before the application deadline will be evaluated. The programme committee may request further information or invite applicants to attend an interview. Shortlisting will be used to evaluate the most relevant applications.

Aarhus University values equality and diversity and encourages all interested candidates to apply, regardless of personal background. Salary and terms of employment are in accordance with the applicable collective agreement. The application deadline is 01 June 2026, and the preferred starting date is 01 August 2026 or later.

For further information regarding the PhD position, contact Associate Professor Behzad Bozorgtabar at [email protected].