project Communication-Optimized Inference in Large Language Models (COIL)

Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No Offer Description Are you interested in the communication networks behind modern AI systems? Would you like to combine mathematical modeling with experiments on programmable network hardware to make AI infrastructure faster and more energy-efficient? In this PhD project, you will develop models and orchestration methods for the networks that connect GPUs during large language model inference. Are you our next PhD candidate in high-performance AI networking? Your research challenge Large language models rely on powerful computing infrastructure to generate responses. When inference is distributed across multiple GPUs, these devices must continuously exchange intermediate results. Network congestion and communication overhead can therefore limit performance and increase energy consumption, even when substantial computing resources are available. In the project Communication-Optimized Inference in Large Language Models (COIL), you will investigate how analytical network models can support the design and operation of AI clusters. The project combines network performance modeling, optimization, and experimental research, giving you the opportunity to connect mathematical foundations with practical challenges in AI infrastructure. You will develop fast, composable analytical models using Network Calculus, a mathematical framework for analyzing communication networks. These models will capture interactions between inference traffic, network architecture, and mechanisms such as flow control and congestion feedback. They will provide bounds on communication latency and buffer requirements, complemented by energy estimates based on measurement-calibrated power models. Building on these models, you will explore how architectural choices-including network topology, link bandwidth, and parallelization strategies-affect performance and energy consumption. You will develop tools that help cluster designers evaluate promising configurations efficiently. You will also investigate how the models can guide runtime decisions, such as workload placement, prioritization, routing, or resource reservation. A focused prototype will demonstrate how model-informed decisions can improve the operation of an existing network. Experimental validation will be an integral part of your research. You will use measurements from AI infrastructure and conduct reproducible experiments on programmable networking testbeds. Technologies of interest include Ethernet-based AI networks, emerging Ultra Ethernet mechanisms, P4-programmable switches, and SmartNICs. Finally, you will evaluate the results from the testbeds on real AI infrastructure in collaboration with our partner . Through this combination of theory, software development, and experimentation, you will contribute to more responsive and energy-efficient AI infrastructure. The project also offers opportunities to share your findings with networking standardization communities and to release research tools and experimental results openly. An interdisciplinary and international environment You will conduct your research under the main supervision of Prof. Lisa Maile who leads the lab. NoMaD is part of the Electronic Systems group in the Department of Electrical Engineering at Eindhoven University of Technology. Your supervision will also include partners from the Advanced Models by Open Research and Engineering Lab of Computer Science and the from Electrical Engineering. The position is funded through the EuroTech programme, which promotes research collaboration between leading technical universities across Europe. As part of this project, you will collaborate closely with Prof. Georg Carle and his research group on at the Technical University of Munich (TUM). As part of this collaboration, you will spend six-month in Munich with the group at TUM, where you will gain hands-on experience with programmable network hardware and reproducible experimental infrastructure. Where to apply Website Requirements Specific Requirements

• A master’s degree in Electrical Engineering, Computer Science, Computer Engineering, Applied Mathematics, or a closely related field.
• A strong mathematical background, demonstrated by excellent performance in mathematically rigorous courses, additional mathematics electives, a mathematics minor or specialization, or substantial mathematical work in a thesis or research project.
• Good programming skills and an interest in developing research software and experimental tools.
• Strong analytical and problem-solving skills, initiative, and creativity.
• An interest in high-performance networking and AI infrastructure, and motivation to apply mathematical methods to computer networks and distributed systems.
• A strong team spirit and enthusiasm for working in an international, collaborative, and socially engaging environment.
• Excellent oral and written communication skills in English.
• Willingness to spend at least six months at the Technical University of Munich (TUM) as part of the project., * A solid foundation in computer networks or distributed systems.
• Experience with Network Calculus, network simulation, mathematical optimization, or GPU communication.
• Experience with programmable networking technologies, such as P4 or SmartNICs., * Curriculum vitae, including a list of your publications and the contact information of three references. Kindly note that we may reach out to references at any stage of the recruitment process. We recommend notifying your references upon submitting your application.
• A transcript of your BSc and MSc studies.
• A sample of your academic or technical writing in English where you are the first authors. For example, a research paper, thesis chapter, or report, of which you are the primary author.

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate assessment after nine months. You will spend a minimum of 10% of your four-year employment on teaching tasks, with a maximum of 15% per year of your employment.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the

, scale P (min. € 3,204 - max. € 4,051 gross base salary per month (full-time)). * In addition to your base salary, you will receive an 8% holiday allowance and an 8.3% year-end bonus, both calculated based on your annual gross base salary.

• Generous leave options: a standard 29 days (based on a 38 hour working week) per year that you can increase to 41 days by working two hours more per week (flexible working hours). This is prorated if you work part-time.
• As a TU/e employee, you participate in the ABP pension scheme, providing retirement pension and pension benefits for surviving dependents and occupational disability. TU/e pays 70% of the pension premium, while employees contribute the remaining 30%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own

. * An excellent technical infrastructure, and on-campus children’s day care.

• Unlimited access to the modern on-campus

at an exceptionally affordable rate. * We support your wellbeing with free 24/7 access to OpenUp, providing you and your family with mental health support, expert guidance, and online training.

• An allowance for commuting, working from home and internet costs.
• A