Careers Denmark
Se alle job

Research & Development

Postdoc Position: Adaptive and Distributed Foundation Model Inference across the Computing Continuum

Aarhus Universitet (AU) Denmark Publiceret 28. okt. 2026 Frist 4. jan. · 48 dage tilbage Arbejdsgiverens karrieresideMidlertidigFuldtidErfarenEngelsk

Resumé

Conduct research on adaptive, distributed foundation model inference across edge and cloud computing resources, including collaborative inference, model placement and scheduling, compression, and resource-aware optimization.

Felterne er læst af AI fra opslaget. Har arbejdsgiveren selv udfyldt et felt, bruger vi det.

Kort om jobbet

Institut for Elektro- og Computerteknologi - Communication, Control and Automation - Fakultet:

Technical Sciences

Postdoc Position

Adaptive and Distributed Foundation Model Inference across the Computing Continuum

Ansøgningsfrist

  • jan. 23:59 CET

Forventet start

  • mar.

-

Institut for Elektro- og Computerteknologi - Communication, Control and Automation

Helsingforsgade 10

8200 Aarhus N

-

Tidsbegrænset fuldtidsstilling

  • mar. 2027 - 28. feb. 2029

ID: 171689

Søg stillingen

We are seeking highly motivated and talented applicants for a 2-year postdoctoral position (with the possibility of extension) in the area of distributed foundation model inference.

Join us at the Department of Electrical and Computer Engineering, Aarhus University, where we are advancing resource-efficient and distributed foundation model inference across the computing continuum, leveraging the computation resources at Edge and Cloud. Our research aims to enable scalable, low-latency, and resource-aware deployment of large foundation models.

Expected start date and duration of employment

This is a full-time, fixed-term position for two years, starting on March 1, 2027, or as soon as possible thereafter.

The initial appointment will run until Feb 28, 2029, or for 24 months from the actual start date.

Job description

  • The successful candidate will contribute to cutting-edge research on topics including:
  • Distributed and collaborative inference strategies;
  • Mixture-of-Experts (MoE) placement and scheduling for inference acceleration;
  • Token compression or Intermediate feature compression;
  • Resource-aware and communication-efficient inference optimization.

You will work in a dynamic and collaborative research environment, with opportunities to publish in top-tier venues and collaborate with leading academic and industry partners within the Horizion Europe Project.

Your profile

We are looking for a highly motivated and talented candidate with a background in deep learning.

Dette er et uddrag. Læs hele opslaget hos Arbejdsgiverens karriereside