R&D Engineering Internship: Reduction of Physical Models through Deep Learning M/F Brognard (25)

Company Description

Accelerate your career within a fast-growing global engineering group. At SEGULA Technologies, you will work on exciting projects and help shape the future within a company where innovation is linked with engineering.

3D printing, augmented reality, autonomous vehicle, factory of the future... daily life for our 13,000 talented collaborators, perhaps yours too?

Across the street or the other side of the planet, you will find opportunities at SEGULA Technologies that will give new meaning to your career!

Job Description

As part of our Research and Innovation projects within our BROGNARD agency, you will work on the reduction of complex physical models using Deep Learning models, better able to capture non-linear dependency relations. The main goal of the study will be to find the best balance between the reduction of calculation time compared to complete models and the preservation of the accuracy of solutions.

The envisioned approach is as follows:

• Research on model reduction methods, particularly for PDEs nonlinearly dependent on time
• Searching for optimization solutions for deep learning models through concrete physical principles.
• Developing model reduction solutions based on different Deep Learning architectures (auto-encoders, LSTM...)
• Conversion of 3D models into 0D/1D system models to optimize control command
• Case study for the introduction of the solution into digital twins in place of the finite element method

Qualifications

You are looking for an internship as part of your +5 bachelor's degree course with a specialization in mathematical engineering

You are interested in new technologies and technical jobs.

You have good knowledge of mathematics and Deep Learning.

Knowledge of Python and MatLab programming.

Dynamic, motivated and rigorous, you have a real desire to learn and you enjoy teamwork, join our organization with the desire to express your talents.

Additional Information

Duration of the internship: 6 months

Start of the internship: February-March 2024