Postdoc Position: Efficient foundation model inference across the computing continuum Full-time

Postdoc Position: Efficient Foundation Model Inference Across The Computing Continuum

We are seeking highly motivated and talented applicants for a 1-year postdoctoral position (with the possibility of 1-2 year extension) in the area of efficient foundation model inference. Join us at the Department of Electrical and Computer Engineering, Aarhus University, where we are advancing communication-efficient and distributed foundation model inference across the computing continuum — from Cloud to Edge. Our research aims to enable scalable, low-latency, and resource-aware deployment of large foundation models.

This is a full-time, fixed-term position for one year, starting on September 1, 2026, or as soon as possible thereafter. The initial appointment will run until August 31, 2027, or for 12 months from the actual start date. An extension of 1–2 additional years may be offered, subject to satisfactory performance.

The successful candidate will contribute to cutting-edge research on topics including:

• Token compression and adaptive token pruning;
• Distributed and collaborative inference strategies;
• Mixture-of-Experts (MoE) architectures for scalable inference;
• Resource-aware and latency-constrained inference optimization;
• Edge intelligence and on-device foundation model deployment.

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.

We are looking for a highly motivated and talented candidate with a background in deep learning. The required qualifications include:

• Ph.D. in Computer Science, Computer Engineering, Electrical Engineering or a related field;
• Strong background in Deep Learning (e.g., Transformers, foundation models);
• Strong programming skills in Python and experience with deep learning frameworks (e.g., PyTorch);
• Experience with distributed systems and edge AI;
• Strong publication record in reputable conferences or journals relative to career stage;
• Excellent written and spoken English communication skills.

The following qualifications will be considered as an advantage:

• Experience in working with stream data;
• Experience in working with Goal-oriented Communications;
• Experience with collaborative, cross-cultural research environments.

You will be based at the Department of Electrical and Computer Engineering (ECE) at Aarhus University, a dynamic and growing department committed to excellence in research, education, and innovation. Our research spans Internet of things, machine learning, signal processing, to digital twins, all with a strong emphasis on high impact research and societal relevance. This position will be supervised by Professor Qi Zhang, whose research focuses on Edge Intelligence, Goal-oriented Semantic Communications, Internet of Things and Analytics on compressed data.

We offer a vibrant and inclusive research environment with a clear commitment to real-world impact. Denmark is consistently ranked among the best countries in the world for work-life balance and quality of life. Family-friendly policies include generous parental leave, subsidized childcare, and access to excellent public healthcare and education. As a postdoc at Aarhus University, you will benefit from a supportive and flexible workplace culture that values diversity and offers excellent conditions for researchers and their families. Specifically, we offer:

• Access to state-of-the-art facilities and computing infrastructure;
• Strong support for research career development, including mentoring and international networking opportunities;
• A commitment to diversity, equity, and inclusion in all aspects of our work;
• A workplace characterized by professionalism, equality and a healthy work-life balance.

Applications must be submitted by April 30th, 2026.

Shortlisting is used. This means that after the deadline for applications – and with the assistance from the assessment committee chairman, and the appointment committee if necessary, – the head of department selects the candidates to be evaluated. All applicants will be notified whether or not their applications have been sent to an expert assessment committee for evaluation. The selected applicants will be informed about the composition of the committee, and each applicant is given the opportunity to comment on the part of the assessment that concerns him/her self. Once the recruitment process is completed a final letter of rejection is sent to the deselected applicants.