POSTDOCTORAL RESEARCHER

Doctor   Titulación Académica Ingeniería Informática (Titulación Universitaria)   Ingeniería Áreas tecnológicas V- Tecnologías de la Información y las Comunicaciones Idiomas Idioma.
Inglés Nivel Lectura.
Alto Nivel Escrito.
Alto Nivel Conversación.
Alto Idioma.
Español Nivel Lectura.
Medio Nivel Escrito.
Medio Nivel Conversación.
Medio Otros HABILIDADES-CUALIFICACIONES/SKILLS-QUALIFICATIONS.
We are looking for a motivated, creative, inquisitive and innovative candidate with the following qualifications.
• PhD degree within the fields of mechanical, telecommunications or aeronautics.
• Programming skills in Python, also valuable Matlab and C.
Demonstrable experience with Linux OS.
• Experience in advanced signal processing, statistical analysis and machine learning.
• Good communication skills, excellent written and spoken English.
REQUERIMIENTOS ESPECIFICOS/SPECIFIC REQUIREMENTS.
Valuable requirements • Finite Element Method applied to structural mechanics problems; Knowledge on AI frameworks such as TensorFlow, Keras or PyTorch.
BENEFICIOS/BENEFITS.
The candidate will join the “RAPIDO” project team, collaborating in the following tasks.
development and integration of synthetic signal generation; development and training of machine learning models for damage detection, localization and quantification; development and implementation of the “digital twin” for Condition Based Maintenance (CBM) of structures.
The candidate would be integrated into a multidisciplinary group with several years’ experience in the related topics and he/she would attend national or international conferences from the second year of the contract.
Contract conditions• Full time work (37.
h/week).
• Contract Length.
temporary, 2 years.
• Location.
Madrid, Universidad Politécnica de Madrid, Campus Sur.
Possibility of research stay 6-9 months at BSC-CNS Barcelona.
• Annual gross salary.
€.
• Work-Life Balance and Flexibility with very flexible work schedules.
CRITERIOS Y PROCESO DE SELECCION/ELIGIBILITY CRITERIA AND SELECTION PROCESS.
The selection process will adhere to the principles of Open, Transparent, and Merit-based Recruitment (OTMR) as outlined in the European Charter for Researchers.
Technical and personal interviews will be conducted to assess both technical suitability and alignment with the organization’s values and principles.
PhD degree in engineering (mechanical, aeronautical, telecommunications, computer science) is required.
Candidates with additional studies in machine learning or certifications in relevant technologies or methodologies will be considered.
A C1 level or higher in English, both in written and oral comprehension, is mandatory.
We explicitly encourage women, individuals with disabilities, or those with special educational needs to apply, and we ensure non-discrimination in the selection process, retention, and career progression within the institution.
COMENTARIOS ADICIONALES/ADDITIONAL COMMENTS.
RAPIDO aims to provide a rapid predictive tool for safe and intelligent vehicles for civil or defense applications.
Continuous monitoring of the structure's health by employing sensors guarantees the structure's safety at any moment.
For instance, the detection of any anomalies such as impact events caused by bird strike, hail during a storm, or even a tool drop during inspection of the vehicle, can prevent a catastrophic situation.
With a safe, intelligent, and sustainable vehicle, safety and service life are increased, and maintenance costs are reduced.
Focusing on modeling Lamb wave-based Structural Health Monitoring (SHM) systems, the research community has made significant strides in solving the detection and localization of damage in structures.
The project involves a comprehensive approach, combining the generation of a very large and high-fidelity database of damage scenarios with High-Performance Computing (HPC) simulations, and the training of Machine Learning (ML) methods for damage detection, localization and quantification tasks on complex structures.
Particularly, the use of HPC solid mechanics simulations using the finite element method is the key enabler for ML to predict damage variables which are otherwise unfeasible to characterize experimentally, paving the path to innovative research for new damage prediction algorithms.