postdoctorat M/F lois de conservations hyperbolique et controle

Job Description

Missions

Exploration of the interface between traditional control and machine learning, within frameworks ranging from ODEs to hyperbolic conservation laws.
Collaboration with existing team members working in the fields of PDEs and control or machine learning, with the aim of fostering stronger links between the two communities.
Participation in the scientific life of the team and the laboratory, particularly through seminars and working groups.

Activity

- Development of hybrid methods combining classical closed-loop control and machine learning.
- Leveraging deep learning libraries (e.g., PyTorch) to develop efficient, tailored numerical code.
- Exploration of inverse problems using PDE-based and statistical methods.
- These approaches will be applied to models ranging from ordinary differential equations to hyperbolic conservation laws and Hamilton-Jacobi equations.

Your Profil

Skills

Scientific experience in the following areas:
- Open-loop and closed-loop control
- Numerical schemes and simulation
- Machine learning
- Entropy solutions to conservation laws

Expected Professional and Interpersonal Skills (Soft Skills):
The candidate must demonstrate a high degree of autonomy in conducting their research, alongside a strong ability to adapt when facing complex theoretical bottlenecks. Excellent interpersonal and communication skills (both written and verbal, in French or English) are essential for collaborating effectively, sharing research progress, and promoting the laboratory's work.

Your Work Environment

The Institut Denis Poisson is a laboratory for Mathematics and Theoretical Physics, located across two sites in Orléans and Tours. It has approximately 90 permanent researchers and faculty members, around thirty PhD students, ATERs (temporary teaching and research assistants), and postdocs, as well as a dozen teaching and research support staff. Research is organized around four thematic teams:

Theoretical Physics

PDEs, Modeling, and Simulation

Statistics, Probability, Algebra, Combinatorics, and Ergodic Theory

Analysis and Geometry

The recruited person will be affiliated with the PDEs, Modeling, and Simulation team in connection with the ANR project COSS (Control on Stratified Structure). The actual workplace will be the Institut de Mathématique de Bourgogne in Dijon.

Constraints and risks

Nothing to report

Compensation and benefits

Compensation

3041.58 gross monthly

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions