Phd (M/F) in Reinforcement Learning, application to algorithmic audits

CNRS; France; Sur place; EUR 30 000 - 40 000; Plein temps

Résumé du poste

A prominent research organization in France is seeking a PhD candidate for a full-time research role focused on auditing techniques for machine learning models. The candidate will explore reinforcement learning approaches and contribute to the PACMAM ANR project. This position starts on February 1, 2026, and emphasizes innovative algorithm development and collaboration within a research team.

Qualifications

• Strong background in algorithms and machine learning.
• Experience in reinforcement learning and auditing techniques.
• Ability to conduct research independently and collaboratively.

Responsabilités

• Conduct research on auditing techniques for large machine learning models.
• Develop efficient algorithms for active auditing in the context of reinforcement learning.
• Collaborate with project team members and contribute to progress reports.

Connaissances

Reinforcement learning

Machine learning models

Active auditing techniques

Formation

PhD in Computer Science or Mathematics

Description du poste

Organisation/Company CNRS Department Laboratoire d'analyse et d'architecture des systèmes Research Field Computer science Mathematics » Algorithms Researcher Profile First Stage Researcher (R1) Country France Application Deadline 28 Nov 2025 - 23:59 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 1 Feb 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Localised at LAAS, in the context of the PACMAM ANR project: PACMAM aims to enable practical audits of black-box in-vivo models.
To that end, it will address to key challenges: first by devising request-
efficient solutions that requires the auditor a low budget to conduct her
audit. Second, providing solutions that are tractable on modern models.
Finally, by coping with models dynamism, leveraging previous audit results
to improve the following ones.

Exploration of active auditing techniques for large machine learning models, use of reinforcement learning, potential application to recommender systems.
The PhD will mainly investigate the use of reinforcement learning approaches to enable tractable active auditing, by both relaxing guarantees and by adding work assumptions for proposing efficient algorithms.