Applications are invited for a PhD position at the IMDEA Software Institute in Madrid, Spain, that will be partially funded by the Madrid Regional Government (César Nombela grant 2024-T1/COM-31302).
The successful candidates will join the research lab under the supervision of Dr. Thaleia Dimitra Doudali.
The dissertation aims to significantly improve the energy efficiency and sustainability of cloud computing systems by addressing the widespread issue of low resource utilization in data centers. It focuses on developing advanced, AI-driven forecasting models and resource management techniques, such as overcommitment and autoscaling, to optimize hardware usage and reduce CO₂ emissions. By combining lightweight machine learning with robust heuristics, the project seeks to deliver open-source tools and practical solutions that can be adopted in real-world cloud infrastructures.
Who should apply?
The position requires good programming and problem solving skills and proficiency in spoken and written English. A background on machine learning and operating systems (course work, coding experience etc.) is highly desirable.
Working at IMDEA Software
The IMDEA Software Institute is ranked among the best European research institutes in computer science. The institute provides an internationally competitive stipend and support for research related travel. The working language at the institute is English. Knowledge of Spanish is not required.
Dates
The position will cover the whole duration of the doctoral studies. The starting date is October 2025. Deadline for applications is August 8th, 2025. Review of applications will begin immediately, and continue until the position is filled.
How to apply?
Applicants interested in the position should submit their application at https://careers.software.imdea.org/ selecting option PhD student and reference code 2025-07-phd-sysml.
The recruitment process will comply with the IMDEA Software Institute’s OTM-R Policy.
For any questions about these positions, please contact Thaleia Dimitra Doudali directly ().
