Doktorand inom inom maskininlärning för strömningsmekanik
Core
Developing reliable probabilistic methods for inference, optimization, and data assimilation to integrate simulations and experimental data for designing, predicting, and controlling complex turbulent flow systems carrying electric charge.
Role type
PhD researcher in probabilistic machine learning for fluid mechanics
Builds
Reliable tools for design, prediction, and control of complex flow systems (e.g., in power transformers)
Domain
Fluid mechanics / Machine learning / Electrical infrastructure
Deliverable
production ML models
Required skills
Probabilistic machine learning, Bayesian inference, Statistical methods, Data assimilation, Simulation integration, Experimental data analysis
Preferred skills
Turbulence modeling, Generative AI, Fluid mechanics background
Technologies
Probabilistic methods, Simulation tools, Experimental measurement systems
Responsibilities
Develop probabilistic methods for inference and optimization, Integrate simulation and experimental data, Calibrate models and quantify uncertainties, Select experiments for complex flow systems
Seniority
PhD candidate (Researcher)