14 Oct 2026
Job Information
Organisation/Company: Inria, the French national research institute for the digital sciences
Research Field: Computer science; Mathematics
Researcher Profile: First Stage Researcher (R1)
Application Deadline: 13 Nov 2026 - 00:00 (UTC)
Country: France
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 38.5
Offer Starting Date: 1 Dec 2026
Is the job funded through the EU Research Framework Programme? Horizon 2020
Reference Number: 2026-10601
Is the Job related to staff position within a Research Infrastructure? No
Offer Description
The position will be in the framework of the ERC Starting Grant DYNASTY (Dynamics-Aware Theory of Deep Learning).
The position might include traveling to conferences for paper presentation. Travel expenses will be covered within the limits of the scale in force.
We are seeking a Machine Learning Engineer to design and develop a Python software library for evaluating theoretical generalization bounds in deep learning.
The objective is to bridge the gap between theoretical advances in learning theory and practical deep learning by providing a modular, efficient, and user-friendly framework for computing and comparing generalization bounds on modern neural networks.
- Conduct experiments for empirical verification
- Prepare software libraries
- Write scientific articles
- Disseminate the scientific work in appropriate venues.
Where to apply
Website: https://jobs.inria.fr/public/classic/en/offres/2026-10601
Requirements
Skills/Qualifications
- Strong Python programming skills and experience with PyTorch.
- Solid understanding of machine learning and deep learning.
- Experience in scientific software development, testing, and version control.
- Familiarity with statistical learning theory and generalization bounds is a plus.
- Ability to work collaboratively with researchers and translate mathematical concepts into reliable software.
Languages
FRENCH
Level: Basic
ENGLISH
Level: Good
Additional Information
Benefits
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
Selection process
Website for additional job details: https://jobs.inria.fr/public/classic/en/offres/2026-10601
Work Location(s)
Number of offers available: 1
Company/Institute: Inria
Country: France
City: Paris
Contact
City: LE CHESNAY CEDEX
Website: http://www.inria.fr
Street: Domaine de Voluceau - Rocquencourt
Postal Code: 78153