Summary:
Aarhus University invites applications for a fully funded PhD fellowship in the Department of Electrical and Computer Engineering. The research project focuses on developing robust machine learning systems that can adapt during test time to real-world distribution shifts.
PhD Position in Test-Time Adaptation and Agentic AI, Aarhus University, Department of Electrical and Computer Engineering, 8200 Aarhus N, Denmark
Designation:
PhD Candidate
Location:
Aarhus University, Department of Electrical and Computer Engineering, 8200 Aarhus N, Denmark
| Criteria | Details |
|---|---|
| Research Area | Adaptive & Agentic AI |
| Eligibility | Master’s degree in a relevant field |
| Start Date | 01 August 2026 or later |
| Application Deadline | 01 June 2026 at 23:59 CEST |
Eligibility/Qualifications:
- Master’s degree (120 ECTS) in Electrical Engineering, Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a related field.
- Strong background in machine learning or computer vision.
- Solid programming skills in Python and experience with deep learning frameworks (e.g., PyTorch).
- Prior research experience (master’s thesis, publications, or substantial research projects) is advantageous.
Job Description:
The PhD candidate will develop methods for test-time adaptation in multimodal foundation models. Key responsibilities include:
- Designing algorithms for adaptive systems that detect distribution shifts and apply updates.
- Exploring feedback-driven and reward-based adaptation, uncertainty estimation, and out-of-distribution detection.
- Collaborating internationally and publishing at leading venues (NeurIPS, ICML, ICLR, CVPR, ECCV).
How to Apply:
Interested candidates should submit the following documents:
- A 1-page statement of interest detailing background and research fit.
- A CV, including a publication list (if any).
- Academic transcripts and diplomas.
Applications must be submitted via the provided link.
Last Date to Apply:
01 June 2026 at 23:59 CEST.
For further inquiries, contact Associate Professor Behzad Bozorgtabar at behzad@ece.au.dk.
