Post doc - Distributed Knowledge Bases for Semantic Communications
ref :2025-43873 | 04 Apr 2025
apply before : 30 Sep 2025
- 28 Chemin du Vieux Chêne, 38240 MEYLAN - France
about the role
Your role as a Post-doctoral researcher will focus on "Distributed Knowledge Bases for Semantic Communications."
This post-doctoral position is part of the SNS 6GARROW collaborative project, which aims to develop AI-native 6G architecture, optimize networks through AI agents, and explore semantic communications (https://6garrow.com).
Background: Large Language Models (LLMs) are experiencing rapid and continuous evolution, now incorporating multimodal capabilities, reasoning, and action functions. This evolution enables the emergence of new AI agent services, deployed as personal or professional assistants. These agents will need to collaborate autonomously to process user requests, gradually transforming these services into machine-to-machine interactions.
Challenge: For effective communication, AI agents must precisely define the data to be transmitted and correctly interpret received information, both aspects being dependent on the communication context. This context materializes through distributed knowledge bases that are not synchronized between sender and receiver. At transmission, the knowledge base helps adapt the query according to context (exchange history, estimation of receiver's knowledge). At reception, the query is enhanced with the receiver's local information to provide better responses. This approach optimizes queries by making them more concise and/or better adapted to the context [1] [2].
Research Objectives:
Develop an innovative evaluation methodology to measure the impact of unsynchronized distributed knowledge bases on Q&A tasks, leveraging Retrieval Augmented Generation (RAG) and context compression [3].
Design models incorporating these knowledge bases in a semantic communication framework to:
Optimize transmitted data compression
Improve task performance
Operate efficiently at both transmission and reception
[1] R. Zhang, et al., "Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networking," arXiv preprint arXiv:2502.16866, 2025.
[2] S. Tang, et al., "Retrieval-augmented Generation for GenAI-enabled Semantic Communications," arXiv preprint arXiv:2412.19494, 2024.
[3] X. Cheng, et al., "xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token," arXiv preprint arXiv:2405.13792, 2024.
about you
Required Profile: You hold a Ph.D. in Computer Science or Signal Processing with a specialization in Artificial Intelligence/Telecommunications.
Required Skills:
Strong expertise in machine learning
Solid understanding of networks and communication systems
Significant experience in Python development, particularly with PyTorch
Prior experience with RAG and related techniques
Track record of publications in international conferences
Personal Qualities:
Methodical approach to research
Strong intellectual curiosity
Ability to work independently
Motivation to tackle open research challenges
additional information
You will join the SNS 6GARROW collaborative project, a consortium uniting prestigious European and Korean partners.
Semantic communications represent an emerging field with broad perspectives in communications. The rise of AI agents and their future collaboration present a particularly promising use case for implementing these communications.
While the impact of context on semantic data exchange between AI agents was identified in early publications, initial research focused on more pragmatic aspects. Today, the evolution of language models and the emergence of RAG techniques provide the necessary tools to address this challenge more directly. This post-doctoral position offers an opportunity to contribute to shaping the future of AI agent communications.
Benefits: The selected candidate will receive full Orange benefits, including works council membership and profit-sharing schemes.
department
Orange Innovation brings together the research and innovation activities and expertise of the Group's entities and countries. We work every day to ensure that Orange is recognized as an innovative operator by its customers and we create value for the Group and the Brand in each of our projects. With 740 researchers, thousands of marketers, developers, designers and data analysts, it is the expertise of our 6,000 employees that fuels this ambition every day.
Orange Innovation anticipates technological breakthroughs and supports the Group's countries and entities in making the best technological choices to meet the needs of our consumer and business customers.
Within Orange Innovation, you will join a research team with dual expertise in artificial intelligence and signal processing. You will work alongside researchers focusing on innovative and foundational topics for the future of telecommunications, particularly 6G. This position is offered for one year with possibility of renewal.
contract
Post Doc
Only your skills matter
Regardless of your age, gender, origin, religion, sexual orientation, neuroatypia, disability or appearance, we encourage diversity within our teams because it is a strength for the collective and a vector of innovation. Orange Group is a disabled-friendly company: don't hesitate to tell us about your specific needs.
Similar offers
Orange SA
Orange Group
of our employees are proud to work for Orange
recommend Orange as a good place to work
is the candidate experience in France, in the category of companies with over 1,000 employees
Since 2011, Orange has GEEIS (Gender Equality European & International Standard) certification in some twenty countries