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 August 2026 or later. You can submit your application via the link under 'how to apply'.

Title:
PhD Position: Agentic Test-Time Adaptation for Efficient and Reliable Edge Intelligence

Research area and project description:
We invite applications for a fully funded PhD position at Aarhus University within the Department of Electrical and Computer Engineering. The successful candidate will join the newly established A3 Lab – Adaptive & Agentic AI, directed by Dr. Behzad Bozorgtabar, who will serve as the primary supervisor. The research is co-supervised in close collaboration with Prof. Qi Zhang, providing a unique interdisciplinary environment at the intersection of Foundation Models and Edge Intelligence.

Project Vision. Deploying Foundation Models at the edge environments requires navigating a fundamental conflict between model complexity and environmental volatility. Real-world edge environments are highly dynamic: data streams from sensors and cameras are subject to "domain shifts" caused by fluctuating conditions, hardware degradation, or changing physical surroundings. 

Traditional AI models are often brittle under these distribution shifts, leading to unreliable outputs that can compromise safety in mission-critical applications—ranging from autonomous robotics to real-time industrial monitoring. To maintain performance without the latency penalties of cloud-based recalibration, AI systems must become "self-aware" and capable of autonomous evolution.

Key Research Objectives. The objective of this PhD is to develop a high-performance, low-latency framework for Test-Time Adaptation (TTA). This involves designing autonomous architectures capable of monitoring and maintaining the reliability of unimodal and multimodal foundation models in real-time. Key research pillars include:

• Autonomous Monitoring: Developing mechanisms to detect distribution shifts and quantify model uncertainty across heterogeneous data types.
• On-the-Fly Adaptation: Designing lightweight TTA algorithms that can recalibrate models at the edge under strict latency and computational constraints.
• Efficiency and Reliability: Balancing the trade-offs between adaptation accuracy, energy efficiency, and hard real-time execution.

The successful candidate will join a pioneering research group focusing on the next generation of adaptive AI, with the opportunity to publish at top-tier machine learning and computer vision venues (e.g., NeurIPS, ICML, CVPR) and validate research on state-of-the-art edge computing testbeds.

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 to the PhD position must have a master’s degree (120 ECTS) in Computer Science, Computer Engineering, Electrical Engineering, Machine Learning, or a related quantitative field.

• Technical Skills: Advanced proficiency in Python and deep learning frameworks (e.g., PyTorch).
• Core Knowledge: A strong foundation in machine learning and/or computer vision. The candidate should have a specific interest in Test-Time Adaptation, Continual Learning, Machine Unlearning, Foundation Models (Vision-Language, Multimodal), or autonomous AI systems.
• Advanced Architectures & Edge AI: Familiarity with modern neural network architecture (e.g., Transformers, advanced CNNs) is required. Experience with model compression techniques tailored for the edge — such as Knowledge Distillation, lightweight architecture design, or parameter-efficient fine-tuning — is highly advantageous.
• Attributes: A mindset for reproducibility, open-source contribution, and the ability to work across the boundaries of algorithmic AI and practical edge systems.

Application Requirements (How to Apply) Please make sure your application includes the following documents:

• Statement of Interest (1 page): Detailing your background in ML/CV, experience with Foundation Models, and your motivation for joining the A3 Lab.
• Curriculum Vitae: Including a publication list (if applicable) and technical project portfolio.
• Academic Records: Transcripts and diplomas (Bachelor’s and Master’s). 

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: 

• Behzad Bozorgtabar, behzad@ece.au.dk (main supervisor)
• Qi Zhang, qz@ece.au.dk (co-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 

How to apply:
Please follow this link to submit your application. 

Application deadline is 20 May 2026 at 23:59 CEST. 

Preferred starting date is 01 August 2026.

Please note: 

• Only documents received prior to the application deadline will be evaluated. Thus, documents sent after deadline will not be considered.
• 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.