PhD Position F/M Privacy-Preserving Collaborative Learning of Large Language Models Across Hete[...]

Inria, the French national research institute for the digital sciences; France; Sur place; EUR 40 000 - 60 000; Plein temps

Résumé du poste

A leading research institution in France is offering a PhD opportunity focused on privacy-preserving collaborative learning of Large Language Models. This position, based in Lille, involves designing novel collaborative protocols and evaluating privacy guarantees in machine learning contexts. Ideal candidates should hold a Master's degree in a related field, possess strong programming skills, and be proficient in English. The role offers a stimulating research environment within a prominent team, along with opportunities for national and international collaboration.

Prestations

Partial reimbursement of public transport costs

7 weeks of annual leave

Possibility of teleworking

Professional equipment available

Social and cultural events

Qualifications

• Familiarity with prompt-tuning and in-context learning.
• Interest in privacy-enhancing technologies, especially differential privacy.
• Excellent English proficiency.

Responsabilités

• Conduct original research on privacy-preserving collaborative learning of LLMs.
• Design collaborative protocols and formalize privacy guarantees.
• Evaluate utility-privacy trade-offs and publish findings.

Connaissances

Machine learning

Natural language processing (NLP)

Colloborative learning

Programming in Python

Familiarity with machine learning frameworks

Strong English proficiency

Formation

Master’s degree in computer science, AI, machine learning

Outils

PyTorch

TensorFlow

Description du poste

Inria, the French national research institute for the digital sciences

Organisation/Company Inria, the French national research institute for the digital sciences Research Field Computer science Researcher Profile First Stage Researcher (R1) Country France Application Deadline 15 Jan 2026 - 00:00 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 38.5 Offer Starting Date 1 Apr 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number 2025-09662 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The widespread deployment of Large Language Models (LLMs) has given rise to diverse adaptation paradigms that accommodate varying computational and infrastructural constraints. In addition to traditional full fine-tuning, emerging methods such as prompt-tuning, parameter-efficient tuning like LoRA (Low-Rank Adaptation), and in-context learning for model adaptation with reduced computational resources or without access to model weights. These approaches open up new possibilities for collaborative learning in privacy-sensitive contexts, where multiple clients aim to improve LLM performance without exposing their raw data.

This PhD thesis will focus on designing privacy-preserving collaborative learning strategies for LLMs, starting in a homogeneous setting, where all participants rely on the same adaptation paradigm. This initial step will build a foundation for tackling the more ambitious and impactful goal of heterogeneous collaboration, where clients operate under different adaptation regimes due to diverse privacy, computational, or architectural constraints. A central challenge of the project is to reconcile contributions from such heterogeneous clients in a unified learning process, while ensuring rigorous privacy guarantees—most notably through differential privacy (DP), which provides strong theoretical protections against data leakage. The thesis will also address the trade-offs between model utility and privacy risk and propose novel mechanisms specifically tailored to this multi-paradigm collaborative learning scenario.

The PhD candidate will be based at Inria Lille, within the MAGNET research team, and will be co-supervised by M. Tommasi, Dr. Raouf Kerkouche (Inria Lille) and Dr. Cédric Gouy-Pailler (CEA Saclay). The research will benefit from a stimulating scientific environment, combining Inria’s strong expertise in machine learning and artificial intelligence with the applied research focus of the CEA. This thesis is part of the REDEEM project, funded by the PEPR IA initiative (France 2030). It offers a highly interdisciplinary environment bridging machine learning, natural language processing,and privacy-enhancing technologies, with opportunities for national and international collaboration.

The person hired will carry out original research toward a PhD on “Privacy-Preserving Collaborative Learning of Large Language Models Across Heterogeneous Learning Paradigms.” The research will involve designing novel collaborative protocols, formalizing privacy guarantees, and evaluating theimpact of different learning paradigms on performance and privacy.

The candidate will get acquainted with the state of the art on privacy-preserving collaborative learning and adaptation of Large Language Models (LLMs), perform original research in close interaction with the thesis supervisors and other collaborators, and design collaborative learning strategies across heterogeneous adaptation paradigms such as full fine-tuning, prompt-tuning, and in-context learning. A key part of the work will involve developing and analyzing privacy-preserving mechanisms—particularly those based on differential privacy, which offers strong theoretical guarantees against data leakage. The candidate will evaluate these mechanisms in terms of their utility-privacy trade-offs, write scientific articles detailing the results, and present the work at top-tier international conferences and leadingpeer-reviewed journals in the areas of machine learning, privacy, and natural language processing.

• Master’s degree in computer science, artificial intelligence, machine learning, natural language
  processing, applied mathematics, or a related field.
• Solid foundations in machine learning and natural language processing (NLP), including familiarity
  with training and fine-tuning large language models (LLMs), as well as an understanding of recent
  trends such as prompt-tuning and in-context learning.
• Experience or strong interest in collaborative learning.
• Familiarity with privacy-enhancing technologies, in particular differential privacy, is a plus.
• Strong programming skills, preferably in Python, and experience with machine learning frameworks
  such as PyTorch or TensorFlow.
• Excellent oral and written English proficiency.

Languages FRENCH Level Basic

Languages ENGLISH Level Good

Additional Information

• 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