Internship: Active Learning for Fundational PDE Surrogates
Inria · Saint Martin d'Hères
Research instituteonsiteinternship$10k
At a glance
Highlights
- Extend OGAS active learning to train one surrogate across multiple PDEs.
- Tackle trajectory stability to reduce error buildup over long rollouts.
- Steer PDE solver data generation dynamically to improve generalization.
What they offer
- Access to GPU supercomputers for experiments
- Leverage Melissa software suite for online surrogate training
- Minimum 4-month internship with flexible start date
Ideal candidate
Motivated master's student fascinated by applying AI to physics, eager to learn quickly and tackle open research on generalization and stability.
Requirements
- Master M2 or engineering school (PFE) student
- Basic knowledge of probabilities, deep learning and physics
- Confident programming skills to develop DL algorithms in PyTorch or JAX
- Motivation to quickly learn new things
- Interest in application of AI to physical sciences
- English communication skills
- hiring process
- Apply with CV, recent university marks and pointers to personal work; 2-month administrative delay before start.
Lab profile
About Inria
French national research institute advancing digital sciences, computing, AI and applied mathematics.
What they build
- Digital sciences and computing research
- Artificial intelligence for microscopy and video analysis
- Quantum information theory
Known for
- Joint teams with Paris-Saclay University and Institut Polytechnique de Paris
- Embedded in Paris-Saclay science and technology cluster
- Rich R&D ecosystem with startups, industry and clusters
- International collaborations and multinational scientific staff
Key facts
- Founded in 1967
- Headquartered in France
- Nine research centres across France
First seen · Last seen