Hjem » PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments

PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments at Aarhus University

Stilling PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments
Opslået 23 Jun 2026
Udløbet 23 Jul 2026
Virksomhed Aarhus University
Lokation Aarhus | DK
Jobtype Full Time

Jobbeskrivelse:

Seneste jobinformation fra Aarhus University til stillingen som PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments. If the PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments ledige stilling i Aarhus matcher dine kvalifikationer, bedes du indsende din ansøgning eller dit CV direkte gennem den opdaterede Jobkos jobportal.

Bemærk venligst, at det ikke altid er nemt at søge job, da kandidater skal opfylde visse krav sat af virksomheden. Vi håber, at karrieremuligheden hos Aarhus University til stillingen som PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments nedenfor matcher dine kvalifikationer.

Title

PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments

Overview

Applicants are invited for a fully funded PhD fellowship at the Graduate School of Technical Sciences, Aarhus University, Danmark, within the Electrical and Computer Engineering programme. The successful candidate will join the A3 Lab – Adaptive & Agentic AI, supervised by Dr. Behzad Bozorgtabar and co‑supervised by Prof. Qi Zhang. The Stilling is available from 01 November 2026 or later.

Research Vision and Objectives

Deploying models in edge environments requires balancing model complexity with environmental volatility. Real‑world edge data streams face continuous domain shifts, causing brittle AI models. This PhD will develop a high‑performance, low‑latency framework for Test‑Time Adaptation (TTA) to maintain model reliability on the edge. The research focuses on:

  • Autonomous monitoring of distribution shifts and model uncertainty across heterogeneous data types.
  • On‑the‑fly, lightweight adaptation algorithms for strict latency and computational constraints.
  • Balancing adaptation accuracy, energy efficiency, and real‑time execution.
Responsibilities

Design and implement autonomous architectures for monitoring and maintaining the reliability of unimodal and multimodal foundation models in real time; develop and evaluate lightweight TTA algorithms; balance trade‑offs between accuracy, efficiency, and real‑time constraints; publish results at top‑tier machine learning venues; validate research on state‑of‑the‑art edge computing testbeds.

Qualifications

Applicants must hold a master’s degree (120 ECTS) in Computer Science, Computer Engineering, Electrical Engineering, Machine Learning, or a related quantitative field. Desired technical and research competencies include:

  • Advanced proficiency in Python and deep learning frameworks such as PyTorch.
  • Strong foundation in machine learning and/or computer vision, with a specific interest in test‑time adaptation, autonomous AI systems, and edge intelligence.
  • Familiarity with modern neural networks and edge‑specific model compression techniques (knowledge distillation, lightweight design, parameter‑efficient fine‑tuning).
  • Mindset for reproducibility, open‑source contribution, and cross‑disciplinary collaboration.
Lokation

Aarhus University, Adaptive & Agentic AI (A3) Lab, Department of Electrical and Computer Engineering, Faculty of Technical Sciences, Aarhus University, Danmark.

EEO Statement

Aarhus University’s ambition is to be an attractive and inspiring workplace for all. We view equality and diversity as assets and welcome all applicants regardless of personal background.

#J-18808-Ljbffr

Jobinfo:

  • Virksomhed: Aarhus University
  • Stilling: PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments
  • Arbejdssted: Aarhus
  • Land: DK

Sådan indsender du en ansøgning:

Efter at have læst og forstået kriterierne og minimumskravene til kvalifikationer forklaret i jobinformationen PhD Stilling in Efficient Test-Time Model Adaptation in Dynamic Edge Environments at the office Aarhus ovenfor, bedes du straks færdiggøre dine ansøgningsdokumenter såsom ansøgning, CV, kopi af eksamensbevis og andre bilag som forklaret. Indsend via linket 'Næste side' nedenfor.

Næste side »

Lignende ledige stillinger

  Teamlead at BaseForce
Opslået: 1 day ago

Beskr.: Team Leader – Part‑time (Aarhus, Danmark)We are searching for a skilled and motivated individual to join our team as a part‑time Team Leader. You will be responsible for managing and coordinating the...

Virksomhed: BaseForce | Lokation: Aarhus
  Job-aggregator 2026
Om os
Privatlivspolitik
Ansvarsfraskrivelse
Vilkår og betingelser
Kontakt os
Indsend XML Feed

© Jobkos

  Ved at besøge Jobkos' hjemmeside og bruge vores tjenester, accepterer du at være bundet af følgende vilkår og betingelser.
Oprettet af Jobkos | | | |