PhD Position: AI-driven computational models for battery degradation

h3PhD Position: AI-driven computational models for battery degradation /h3 p12-Oct-2026 /p pResearch Development /p pSiemens Industry Software NV /p pProfesional Junior /p pTemporal /p pbPhD Position in AI-driven computational models for battery degradation /b /p pAs part of the recently launched bMSCA-DN /b (Marie Skłodowska-Curie Actions Doctoral Network) project funded by the European Union, titled bTRAIN-FAST /b (Training Researchers in Adaptive, Integrated and Safe Technologies for Ultra-Fast Battery Charging), bSiemens Industry Software NV (SISW) /b has a PhD position to collaborate in the development of a Digital Twin for predictive ultra-fast charging. This PhD is in bcollaboration with Politecnico di Torino /b (POLITO) where the PhD degree will be awarded. /p pTransportation accounts for approximately one-third of global energy-related carbon dioxide emissions and is undergoing a profound transition towards electric mobility and renewable energy integration. Ultra-fast charging technology is critical for providing charging convenience comparable to conventional refuelling and for accelerating the widespread adoption of electric vehicles. The baim of TRAIN-FAST is to educate the next generation of leading scientists and engineers who will advance ultra-fast charging technology /b within the broader electric-mobility ecosystem. The programme adopts an interdisciplinary approach, combining advanced engineering, data science, techno-economic analysis, and socio-behavioural research to address complex cross-sector challenges. As part of this project, you will have the opportunity to conduct pioneering research at the forefront of battery and charging technology. Please refer to the TRAIN-FAST project website ( ) for further information about the project and the PhD opportunities available at the other recruiting organisations. /p h3Responsibilities and qualifications /h3 pThe PhD researcher will focus on the following activities: /p ul liDevelop a bmulti-scale and multi-physics simulation workflow /b to accelerate battery material screening and cell design capturing coupled electro-chemical, thermal, and mechanical degradation. /li liEmploy a bcombination of ML (Machine Learning) and MOR (Model Order Reduction) techniques /b to efficiently approximate coupled multi-physics partial differential equations across high-dimensional parameter spaces. /li /ul pThese activities will be carried out in close collaboration with the other PhD candidates within the TRAIN-FAST network and with strong support from the industrial partners. /p pYou should have a passion for research in industrial context and a background in modeling and simulation in multi-physics domains (especially in electro-chemistry and mechanical). You will become part of a bmultidisciplinary innovation team located in Leuven (Belgium) /b with a focus on energy topics such as batteries, hydrogen, and covering several application fields from automotive to aerospace. We combine these innovation themes with numerical methods such as MOR and ML in close collaboration with academia. /p pbYour specific tasks will cover: /b /p ul liDevelop physics-based coupled electro-chemical and mechanical models for batteries. /li liInvestigate and derive degradation-related phenomena for specific battery chemistries. /li liDevelop workflows linking physics-based models to light/fast models needed to support control strategies by operator-learning as ML-accelerated ROM with active learning and Bayesian optimisation guiding exploration of the high-dimensional parameter spaces /li liEvaluate and validate numerical models and methods against experimental data and results reported in the scientific literature. /li liDisseminate research findings through scientific publications and presentations at international conferences. /li /ul pYou are expected to take an active role in the international TRAIN-FAST network, participate in secondments at partner organisations, and engage in the network's joint training activities, workshops, and conferences. /p h3Eligibility criteria /h3 ul liTwo-year master's degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master's degree. /li liExperience with numerical modelling or related topics will be advantageous. /li liStrong communication skills in English, both written and oral, are essential. /li liResearchers must be doctoral candidates, i.e. not already in possession of a doctoral degree. You may apply prior to obtaining your master's degree but cannot begin before having received it. Applicants of any nationality are welcome. /li libNote that the MSCA-DN mobility clause applies: /bthe applicant must not have resided or carried out their main activity (work, studies, etc.) in Belgium for more than 12 months in the 36 months immediately before the date of recruitment. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee st