Digital twin for predictive maintenance and structural reliability assessment

Digital twin for predictive maintenance and structural reliability assessment

Ref.: 210422


Development of mechanistic finite element models for structural analysis and machine learning methodologies focused on the inference of surrogate (reduced) models. Integration of these models in a digital twin that recommends optimal operational strategies for structural health maintenance.

Deadline: 31/12/2022

Division/Group: Materials and Manufacturing division, Design and Mechanical Assessment group


Industrial, mechanical, mathematical engineer or similar with Master’s degree

Date of degree: 2020 or later (excluding Final Project).

Language: English

Software: Matlab, Abaqus

Others: Experience in Machine Learning, programming (Python, Matlab, Fortran) and finite element software.


Join a leading technology research company with a clear mission to serve society. Enjoy the opportunity to grow and develop professionally in a positive working environment built on teamwork and trust. Thesis should be completed in 3 years, but may be extended to 4.

Start date: Immediate


  • winter: 7 hours, 45 minutes a day. July and August: 6 hours a day (without a lunch break).
  • Flexitime, starting between 8:00 and 9:30, earliest departure from 16:15.
  • Candidates may choose to leave early on Fridays by working through lunch hour.

Vacation: 23 days + Christmas holiday (24 Dec–2 Jan).


Send the following documentation by email to

  • Cover letter
  • Current CV with photograph
  • Academic Transcript




Telefonoa: (+34) 943 212800