PhD Position in Solid Mechanics: AI-Assisted Natural Fibre Moulding Component Design KTH Royal Institute of Technology in Sweden

This PhD position at KTH Royal Institute of Technology is part of the ENDURE Marie Skłodowska Curie Doctoral Network, focusing on 'AI-assisted natural fibre moulding component design.' The project aims to advance the European moulded fibre products (MFP) industry by developing an AI-based hybrid tool for diagnosis and prognosis in the dry forming of cellulose fibres. This tool will integrate experimental data with physics-based models, bridging the gap between advanced simulations and industrial product development. The doctoral candidate will be hosted at KTH in Stockholm and supported by Yangi AB, gaining experience in both fundamental research and industrial applications.

The research environment is highly international and collaborative, involving five universities, two research and technology organizations, and eight industry partners across four countries. The position offers a dynamic workplace with employee benefits, a competitive monthly salary (starting at 33,000 SEK/month), and additional Marie Curie mobility and family allowances.

The candidate will have opportunities to contribute to industrially relevant research, develop advanced computational and experimental skills, and participate in a unique employability and skills development process. Admission requirements include a second cycle degree (e.g., master's) or equivalent, with at least 240 higher education credits (60 at second-cycle level), and English proficiency equivalent to English B/6. Candidates must not have resided or conducted their main activity in Sweden for more than 12 months in the three years prior to recruitment. Selection criteria emphasize goal orientation, perseverance, independence, collaboration, and analytical skills.

Additional qualifications such as proficiency in numerical methods (FEM), programming (Python, Matlab, C++, Fortran), background in mechanics of materials or computational modelling, and experience with machine learning for physical fields/PDEs/GNNs and HPC workflows are advantageous. The position is full-time, temporary, and renewable up to four years, with a target degree of Doctoral degree. Applications must be submitted through KTH's recruitment system and include a CV, application letter, diplomas, proof of English proficiency, and representative publications.

The application deadline is November 30, 2025. For more information, contact Professor Artem Kulachenko ([email protected]) or Sören Östlund ([email protected]).