KTH Royal Institute of Technology
Top university
Just Landed
New Today
Doctoral student in probabilistic machine learning for fluid mechanics KTH Royal Institute of Technology in Sweden
Degree Level
PhD
Field of study
Computer Science
Funding
Funded by Digital Futures and Hitachi Energy; doctoral student salary according to KTH’s doctoral student salary agreement.
Deadline
Dec 7, 2026
Country
Sweden
University
KTH Royal Institute of Technology
Apply for this position
Keywords
Suggested positions
About this position
KTH Royal Institute of Technology is seeking a doctoral student to join FLOW, a strong research community in the Department of Engineering Mechanics. The position sits within the Fluids and Surfaces Group and is centered on probabilistic machine learning for fluid mechanics.
The project develops trustworthy probabilistic methods for inference, optimization, and data assimilation in fluid systems. A key aim is to combine simulations with experimental data to build reliable tools for the design, prediction, and control of complex flows. The research is motivated by the challenges of fluid mechanics, where flows are high-dimensional, chaotic, and shaped by coupled processes across multiple scales.
A major application focus is turbulent flows carrying electric charge, with power transformers given as an example. These systems are only partly understood, and measurements are sparse and costly, making them a strong testbed for model calibration, uncertainty quantification, and experiment selection. The work is framed as contributing to safer and more sustainable power infrastructure.
The project is supported by Digital Futures and Hitachi Energy. Supervision is proposed by Shervin Bagheri and Ozan Öktem.
The advertised environment combines fundamental and applied research in fluid mechanics with modern AI and scientific computing, offering a doctoral project at the intersection of engineering mechanics, data-driven modeling, and uncertainty-aware methods.
Funding details
Funded by Digital Futures and Hitachi Energy; doctoral student salary according to KTH’s doctoral student salary agreement.
What's required
Applicants must have basic eligibility for postgraduate education, meaning either a second-cycle degree such as a master's degree, or at least 240 higher education credits with at least 60 second-cycle credits, or equivalent knowledge acquired in another way. English proficiency equivalent to English B/6 is mandatory. Experience with fluid mechanics, machine learning, scientific computing, turbulent flows, Bayesian inference, probabilistic methods, and generative AI is meritorious. Candidates are assessed on goal orientation, perseverance, ability to work independently and collaboratively, professional approach, and ability to analyze and work with complex issues.
How to apply
Apply through KTH’s recruitment system. Submit diplomas and grades, proof of language requirements, a CV, a motivation/application letter, and representative publications or technical reports with summaries and links where needed. Ensure the application is complete by the deadline.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.