Postdoctoral Researcher in Efficient Foundation Model Inference Across the Computing Continuum Aarhus University in Denmark

Aarhus University is advertising a Postdoctoral Researcher position in efficient and distributed foundation model inference across the edge-cloud computing continuum. The role sits in the Department of Electrical and Computer Engineering and is linked to research on scalable AI systems, communication-efficient inference, edge intelligence, and resource-aware deployment of large foundation models.

The successful candidate will work on topics such as token compression, adaptive token pruning, distributed and collaborative inference, Mixture-of-Experts architectures, latency-constrained optimization, and on-device foundation model deployment. The postdoc will join a collaborative environment with opportunities to publish in top venues and engage with academic and industry partners in Europe through a Horizon Europe project.

Eligibility highlights: applicants should hold a PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field. Strong experience in deep learning, transformers/foundation models, Python, PyTorch, distributed systems, and edge AI is expected. A strong publication record and excellent English communication skills are required. Experience with stream data, goal-oriented communications, and cross-cultural research collaboration is considered an advantage.

Funding and appointment: this is a full-time, fixed-term postdoctoral appointment for one year starting 1 November 2026, with a possible extension of 1–2 years. Salary is according to Danish collective agreements and depends on seniority. No specific stipend amount is stated.

Application window: the deadline is 30 August 2026. Applications must be submitted in English through Aarhus University’s recruitment system and should include a CV, degree certificate, publication list, research plan, and relevant teaching documentation.

Supervisor/contact: Professor Qi Zhang is listed as the supervisor and contact person.