Summer Sale

Up to 30% off — ends 2 Aug

ONLY00h00m00s

Publisher
source

Aarhus University

Just Landed

PhD Position in Efficient Test-Time Model Adaptation in Dynamic Edge Environments Aarhus University in Denmark

Degree Level

PhD

Field of study

Computer Science

Funding

Full funding available

Deadline

Aug 15, 2026

Country flag

Country

Denmark

University

Aarhus University

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Keywords

Computer Science
Electrical Engineering
Information Technology
Mathematics
Artificial Intelligence
Computer Vision
Domain Adaptation
Robotics
Machine learning

Suggested positions

About this position

PhD opportunity at Aarhus University in the Department of Electrical and Computer Engineering for research on efficient test-time model adaptation in dynamic edge environments. The project focuses on artificial intelligence, computer vision, machine learning, and edge AI, with an emphasis on making unimodal and multimodal foundation models robust under changing real-world conditions.

The research addresses distribution shifts caused by changing surroundings, sensor degradation, hardware constraints, and evolving data streams. The goal is to develop lightweight methods for autonomous monitoring, on-the-fly adaptation during inference, efficient foundation-model adaptation, and reliability under strict latency, memory, and energy limits on edge devices.

The successful candidate will join the Adaptive & Agentic AI (A3) Lab and be supervised by Associate Professor Behzad Bozorgtabar with co-supervision by Professor Qi Zhang. The environment is described as international and collaborative, with opportunities to publish at venues such as NeurIPS, ICLR, and CVPR.

Eligibility highlights include a Master’s degree equivalent to 120 ECTS in computer science, computer engineering, electrical engineering, machine learning, or a closely related quantitative field. Applicants should have strong Python skills and experience with PyTorch. Helpful background includes test-time or domain adaptation, foundation models, multimodal learning, model compression, parameter-efficient fine-tuning, and resource-efficient inference for edge hardware.

This is a fully funded PhD project open to students worldwide. The application deadline is 15 August 2026 at 23:59 CEST. Interested applicants should register their interest via the FindAPhD enquiry form linked in the post.

Funding details

Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.

How to apply

Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?