PhD scholarships in machine learning for optimization of cyber-physical systems

Doctorat / PhD Profil chercheur : First Stage Researcher (R1) Type de contrat : Temporary Date limite de candidature : 24 Nov 2026 - 02:59 (Europe/Copenhagen) Date de début : 1 Jan 2027 Programme UE : Not funded by a EU programme Département : DTU Compute Domaine : Computer science

We offer PhD scholarships at DTU Compute to develop machine learning methods for faster analysis and optimization of cyber-physical systems. You will build predictive models of expensive analytical calculations and simulations, and use AI to find good solutions to optimization problems that cannot be solved exactly within practical computing budgets. You will join the Embedded Systems Engineering section and work with Prof. Paul Pop. The application areas are related to, e.g., software-defined vehicles, datacenters, industrial automation, and energy systems. Responsibilities and qualifications Your research will connect learned prediction models with optimization methods. The PhD topics will be defined with the supervisors. You will: Develop surrogate models that predict results of complex analyses and simulations, such as execution delays, energy use, and resource demands. Use machine learning to guide configuration, scheduling, and resource allocation, reducing the need for expensive model evaluations. Evaluate solution quality, computing time, uncertainty, and transfer to new systems; check proposed solutions against the original models and constraints. Publish your research, collaborate with project partners, and contribute to teaching and student supervision. You must have a two-year master's degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master's degree. Ideally, you have both a BSc and an MSc in machine learning or artificial intelligence. Degrees in computer science, applied mathematics, electrical engineering, or related fields with substantial ML/AI coursework and projects are also relevant. You should have a strong foundation in machine learning, algorithms, probability, and linear algebra; experience implementing and evaluating models in Python; and good written and spoken English. Experience with optimization, reinforcement learning, or simulation is an advantage. Prior expertise in all application areas is not required. Approval and Enrolment The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU's rules for the PhD education . Assessment Assessment will consider academic qualifications, machine learning and programming experience, research potential, and fit with the topic. We offer DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We…