Publisher
source

Lisa Maile

Closing soon

Just Landed

3 days ago

PhD in Communication-Optimized Inference in Large Language Models Eindhoven University of Technology in Netherlands

Degree Level

PhD

Field of study

Computer Science

Funding

Fully funded four-year PhD employment under the EuroTech programme, with a gross monthly salary of €3,204–€4,051 under Collective Labour Agreement for Dutch Universities scale P, plus an 8% holiday allowance and 8.3% year-end bonus. Benefits include pension, leave, commuting and home-working allowances, training, and other employee benefits.

Deadline

Nov 22, 2026

Country flag

Country

Netherlands

University

Eindhoven University of Technology

Apply for this position

Free with an ApplyKite account: the application link, the deadline in your tracker and a check of your fit.

Keywords

Computer Science
Electrical Engineering
Information Technology
Mathematics
Networking
Distributed System
Large Language Models

More like this

Suggested positions

Publisher
source

Eindhoven University of Technology

Country flag

Netherlands

PhD opportunity at Eindhoven University of Technology (TU/e) in the Department of Electrical Engineering, focused on communication-optimized inference in large language models . The project, called COIL , sits at the intersection of computer science , electrical engineering , mathematics , and information technology , with a strong emphasis on AI infrastructure, high-performance networking, distributed systems, and network modeling. You will study how multiple GPUs exchange intermediate results ...

Computer Science
Electrical Engineering
Information Technology
+4 more

4 weeks ago

Publisher
source

Dejan Kostic

KTH Royal Institute of Technology

Country flag

Sweden

This postdoctoral position sits within a 5-year Wallenberg Scholar project on scalable and adaptive inferencing for democratizing AI . The project aims to dramatically reduce the cost and power required to serve large language models such as ChatGPT, and it combines systems research with machine learning ideas to advance practical AI inference. The work is centered at KTH Royal Institute of Technology and is embedded in a research lab environment where the successful candidate will work with fac...

Computer Science
Electrical Engineering
Information Technology
+6 more

2 weeks ago

Publisher
source

DEVCOM Army Research Laboratory

Country flag

United States

This faculty fellowship at the DEVCOM Army Research Laboratory focuses on AI model optimization for inference acceleration in edge computing environments . The project aims to develop theoretical and experimental approaches for accelerating inference on resource-constrained heterogeneous edge platforms, with an emphasis on predicting optimal model architectures through neural network architecture search. The research spans both convolutional neural networks and large language models , with the g...

Computer Science
Electrical Engineering
Information Technology
+4 more

2 weeks ago

Publisher
source

Arash Asadi

Delft University of Technology

Country flag

Netherlands

Delft University of Technology Assistant Professor Arash Asadi announces the recruitment of 15 PhD candidates through RESILIOUS, a research initiative focused on building a more resilient Internet across land, sea, and space . The openings are intended for doctoral researchers working on challenges related to resilient Internet systems and connectivity across diverse physical environments. The post positions the programme within the Marie Skłodowska-Curie Actions (MSCA) context and directs prosp...

Computer Science
Networking

Posted Yesterday

Publisher
source

Leiden University

Country flag

Netherlands

Leiden University is advertising a fully funded 4-year PhD position in Complex Networks , hosted jointly by the Leiden Institute of Advanced Computer Science (LIACS) and the Mathematical Institute (MI) in the Netherlands . The project sits at the intersection of Network Science , Mathematics , and Computer Science , with possible research directions including complex networks , random graph models , spatial networks , algorithmic fairness for networks , mathematical modeling , and data-driven ne...

Computer Science
Information Technology
Mathematics
+2 more

4 weeks ago

About this position

This PhD project investigates how communication networks can be made faster and more energy-efficient for large language model inference. When inference is distributed across multiple GPUs, the devices must exchange intermediate results continuously. Network congestion, communication overhead, and buffer requirements can therefore limit system performance and increase energy consumption.

As part of the Communication-Optimized Inference in Large Language Models (COIL) project, the doctoral researcher will develop analytical models and orchestration methods for networks connecting GPUs in AI clusters. The research will use Network Calculus to create fast, composable models that capture interactions between inference traffic, network architecture, flow control, and congestion feedback. These models will provide bounds on communication latency and buffer requirements and will be complemented by measurement-calibrated estimates of energy use.

The project will examine how network topology, link bandwidth, and parallelization strategies influence performance and energy consumption. The researcher will develop tools to help cluster designers assess configurations and will investigate model-informed runtime decisions such as workload placement, prioritization, routing, and resource reservation. A prototype will demonstrate how these decisions can improve the operation of an existing network.

Experimental validation is central to the project. The researcher will work with AI infrastructure measurements and conduct reproducible experiments on programmable networking testbeds using technologies including Ethernet-based AI networks, Ultra Ethernet mechanisms, P4-programmable switches, and SmartNICs. Results will be evaluated on real AI infrastructure in collaboration with SURF. The work combines mathematical theory, software development, network experimentation, and practical AI infrastructure research, with opportunities to share findings with networking standardization communities and release tools and experimental results openly.

The main supervisor is Professor Lisa Maile, leader of the Network Modeling and Design (NoMaD) lab in the Electronic Systems group of the Department of Electrical Engineering at Eindhoven University of Technology. The research will connect with the Advanced Models by Open Research and Engineering Lab in Computer Science and the Model-Based Design Lab in Electrical Engineering. The doctoral researcher will also collaborate with Professor Georg Carle and the Network Architectures and Services group at the Technical University of Munich, spending six months in Munich to gain hands-on experience with programmable network hardware and reproducible experimental infrastructure.

NoMaD develops mathematical models, tools, and protocols for reliable and efficient communication networks, combining formal analysis with simulation and hardware experiments. The broader Electronic Systems group provides an interdisciplinary environment spanning system architectures, software, digital circuits, predictable performance, timing, reliability, and energy consumption. The project is situated in Eindhoven’s international Brainport technology region and in TU/e’s collaborative research environment focused on high-tech engineering and socially relevant applications.

Funding details

Fully funded four-year PhD employment under the EuroTech programme, with a gross monthly salary of €3,204–€4,051 under Collective Labour Agreement for Dutch Universities scale P, plus an 8% holiday allowance and 8.3% year-end bonus. Benefits include pension, leave, commuting and home-working allowances, training, and other employee benefits.

What's required

Applicants must hold a master’s degree in Electrical Engineering, Computer Science, Computer Engineering, Applied Mathematics, or a closely related field. They must have a strong mathematical background demonstrated through excellent performance in rigorous mathematics courses, additional mathematics study, a mathematics minor or specialization, or substantial mathematical work in a thesis or research project. Good programming skills, interest in research software and experimental tools, strong analytical and problem-solving skills, initiative, creativity, interest in high-performance networking and AI infrastructure, and motivation to apply mathematical methods to computer networks and distributed systems are required. Applicants should have strong team spirit, enthusiasm for international and collaborative work, and excellent oral and written English communication skills. They must be willing to spend at least six months at the Technical University of Munich. Desirable qualifications include foundations in computer networks or distributed systems and experience with Network Calculus, network simulation, mathematical optimization, GPU communication, P4, or SmartNICs. Interviews and a scientific presentation are part of the selection procedure.

How to apply

Apply through the AcademicTransfer application portal using the provided application link. Prepare evidence of the required master’s degree, mathematical and programming background, English communication skills, and relevant research or technical experience; shortlisted candidates will participate in interviews and give a scientific presentation.

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts and confirm requirements with the university.

Professors

Professor at Eindhoven University of Technology

University Name
Country flag

Netherlands

Research Interests

Networking

Wireless Communication

Distributed System

Information Technology

Computer Science

Professor at Eindhoven University of Technology

University Name
Country flag

Netherlands

Research Interests

Distributed System

Networking

Information Technology

Computer Science

Large Language Models