PhD - LLMs for resource allocation in future networksOrange

PhD - 'LLMs as assistants in resource allocation optimization mechanisms in future networks' F/H
Orange Innovation consolidates the Group's research and innovation activities across its entities and countries. With 720 researchers and thousands of marketers, developers, designers, and data analysts, our 6,000 employees drive our goal to position Orange as an innovative operator, creating value through each project. We anticipate technological breakthroughs and support the Group in making optimal technological choices for both consumer and business needs.
As part of the innovation team, you'll work at the forefront of network research and expertise. The MORE (Mathematical Models for Optimization and Performance Evaluation) team focuses on applied mathematics and AI to develop models and techniques for resource optimization and infrastructure performance assessment. Their research aims to identify weaknesses and create analytical tools for designing and planning network infrastructures.

As 6G networks develop, managing RAN resources becomes more complex due to diverse user needs, interference, and system constraints. Traditional optimization methods struggle with scalability and real-time adaptation. Reinforcement learning offers some flexibility but requires extensive training and is sensitive to changes.
Large Language Models (LLMs) show promise in transforming complex problems into simpler, solvable forms and providing explainable, real-time solutions. This thesis explores integrating LLMs with traditional solvers, using techniques like convex relaxation and feedback loops to ensure robust, adaptable solutions. While prior work has addressed resource optimization, it often overlooks real-time constraints. This research aims to overcome these challenges across various 6G scenarios, unlocking LLMs' potential for future wireless networks.

o Master in telecommunications or applied mathematics
o Learning skills(reinforcement learning, Markov decision processes, ...)
o Skills in optimization
o Skills in modeling networks and systems(probabilities, random processes, queues, ...)
o In-depth knowledge in the field of fixed and mobile networks (architectures and protocols, virtualization, SDN, 5G, quality of service management, resource allocation, etc.)
o Programming and IT development skills (Python, Matlab, C / C ++, ...)
o Fluency in written and oral English
o An internship experience in the field of artificial intelligence would be a plus.