kandidatu France

PhD student: physics-informed neural network

IMT Nord Europe · State civil service

En français : Doctorante, réseau de neurones informé par la physique

This job in plain words

This PhD is at IMT Nord Europe in Douai. It aims to build a digital twin that predicts how long a pressure equipment will last, with the CETIM, using AI, physics and lab tests.

Open to non-civil servants

Can you apply?

Civil servants on transfer and public-law contract agents can apply. The job can be adapted for a person with a disability.

Category
Category A (executive)
Diploma
Master's degree (bac+5) · Master 2 or equivalent in scientific computing, applied maths, digital systems, applied AI or related fields
Contract
Civil servant on transfer or public-law contract agent, fixed-term contract (CDD) of 36 months

The profile they want:

  • Master 2 or equivalent in scientific computing, applied maths or AI.
  • Python programming.
  • Use of machine learning and deep learning libraries (PyTorch, TensorFlow...).
  • Knowledge of artificial intelligence and machine learning.
  • Knowledge of predictive maintenance, health monitoring or digital twins.
  • Autonomy, teamwork and communication on technical topics.

What you would do

  • Develop a physics-informed neural network using Python and PyTorch.
  • Model uncertainties to generate realistic scenarios.
  • Optimise the placement of sensors on the equipment.
  • Apply the approach to real structures and compare predictions with measurements.
  • Present results at scientific or industrial conferences and write papers.
  • Take part in teaching, up to 64 hours per school year.

How to apply

You apply by email, as stated on the official offer. The team contacts are listed on the offer page.

Good to know:

  • PhD of about 3 years, starting on 1 October 2026.
  • Work with the CETIM and the ARTS axis of the CERI Systèmes Numériques.
  • Teaching limited to 64 hours per school year.

We wrote this summary automatically from the official offer. Only the offer published on Choisir le Service Public counts: read it before you apply. Source: Choisir le Service Public (DGAFP), Etalab 2.0 licence.

Similar jobs