Post-Doctoral Research Visit – Formal Proofs for Machine Learning: Inria University of Lille is seeking a Post-Doctoral Researcher to join the Scool team, focusing on formal proofs for machine learning algorithms using the Lean theorem prover. This position is an exciting opportunity to work on innovative research at the intersection of machine learning and formal methods.
Post-Doctoral Research Visit – Formal Proofs for Machine Learning
Designation
Post-Doctoral Researcher (F/M)
Table of Job Details
| Attribute | Details |
|---|---|
| Research Area | Optimization, Learning, and Statistical Methods |
| Location | Villeneuve d’Ascq, France |
| Contract Duration | 1 year, 6 months |
| Desired Start Date | January 1, 2026 |
| Application Deadline | September 5, 2025 |
Eligibility/Qualification
- PhD or equivalent in a relevant field.
- Proficiency with Lean or a similar theorem prover.
- Knowledge of mathematical tools required for machine learning theory, particularly probability theory.
- Familiarity with machine learning or bandit algorithms is advantageous.
- Strong scientific communication skills in English.
Job Description
The postdoctoral candidate will:
- Formalize machine learning algorithms, starting with bandit algorithms, in the Lean theorem prover.
- Develop tools for proving theoretical guarantees about these algorithms.
- Manage a collaborative project, including coordinating contributions and reviewing pull requests.
- Disseminate research findings through publications and presentations at conferences.
How to Apply
Interested candidates must submit their applications online through the Inria career portal. Applications sent via alternative channels may not be considered.
Last Date to Apply
September 5, 2025
Additional Benefits
- Subsidized meals and partial reimbursement of public transport costs.
- 7 weeks of annual leave + 10 extra days off.
- Flexible working hours and remote work options.
- Access to professional training and social events.
For inquiries, please contact Remy Degenne at remy.degenne@inria.fr.
