Post-doctoral researcher: LLMs and Ontologies - Controlled Iterative Generation (M/F)
New
- Researcher in FTC
- 24 months
- Doctorate
This offer is available in English version
This offer is open to people with a document recognizing their status as a disabled worker.
Offer at a glance
The Unit
Groupe de recherche en Informatique, Image, Automatique et Instrumentation de Caen
Contract Type
Researcher in FTC
Working hHours
Full Time
Workplace
14032 CAEN
Contract Duration
24 months
Date of Hire
01/10/2026
Remuneration
Between €3,000 and €3,600 gross / month depending on experience
Apply Application Deadline : 07 July 2026 23:59
Job Description
Missions
The recruited researcher's main mission will be to design and develop novel Generative Artificial Intelligence approaches for ontology population from complex texts. Within the framework of the LOGIC project, the agent will hybridize the generative power of Large Language Models (LLMs) with the formal rigor of the Semantic Web to overcome the limitations of static prompt engineering methods. The core objective is to establish a "controlled iterative generation" approach, where a formal ontology acts as a semantic loss function to guide and correct LLMs.
Activity
- Design and implement an automatic prompt optimization mechanism incorporating a feedback loop driven by a formal logic reasoner.
- Develop methods to extract and model complex structures and n-ary relations (e.g., time slots, distances, dependent closures) according to Semantic Web standards (OWL schemas).
- Design an automated evaluation module to align and compare generated predictions with the ground truth (e.g., using an "LLM-as-a-judge" approach).
- Operate, test, and compare various Large Language Models (open-source or proprietary LLMs).
- Write scientific papers and present the obtained results at top-tier international conferences and in leading journals.
- Participate in the scientific life of the host team (project meetings, seminars).
Your Profil
Skills
- Scientific expertise: Solid knowledge in Knowledge Engineering / Semantic Web (Ontologies, RDF, OWL, inference engines) and in modern Natural Language Processing (NLP) including LLM manipulation.
- Programming: Excellent command of Python and/or Java, as well as libraries related to NLP and the Semantic Web.
- Soft skills & Research: Scientific rigor, strong autonomy, proactive mindset, and a proven ability to publish in high-ranking international conferences and journals.
Your Work Environment
The position is open at the GREYC laboratory (UMR 6072 - CNRS, University of Caen Normandy, ENSICAEN). The recruited researcher will be based on Campus 2 in Caen (Normandy, France) and will join the CODAG research team (Constraints, Ontologies, Data, Annotations, Graphs). This work is part of the emerging regional project "LOGIC" (LLMs and Ontologies: Controlled Iterative Generation), funded by the Normandy Region and coordinated by Céline ALEC.
Compensation and benefits
Compensation
Between €3,000 and €3,600 gross / month depending on experience
Annual leave and RTT
44 jours
Remote Working practice and compensation
Pratique et indemnisation du TT
Transport
Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€
About the offer
| Offer reference | UMR6072-CELALE-001 |
|---|---|
| CN Section(s) / Research Area | Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages |
About the CNRS
The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.
Create your alert
Don't miss any opportunity to find the job that's right for you. Register for free and receive new vacancies directly in your mailbox.