
Activez les alertes d’offres d’emploi par e-mail !
Générez un CV personnalisé en quelques minutes
Décrochez un entretien et gagnez plus. En savoir plus
A leading French research agency is seeking a postdoc researcher specializing in machine learning and natural language processing for a 12-month contract. The successful candidate will develop methods for Named Entity Recognition and contribute to a project addressing microbiological risks in food practices influenced by climate change. Candidates should have a PhD and strong programming skills in Python, along with fluency in both English and French. This role offers competitive pay and benefits.
Organisation/Company ANSES Research Field Information science » Other Computer science » Other Researcher Profile First Stage Researcher (R1) Positions Postdoc Positions Country France Application Deadline 12 Dec 2025 - 23:59 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Is the job funded through the EU Research Framework Programme? Other EU programme Is the Job related to staff position within a Research Infrastructure? No
ANSES is looking for post-doc researcher in the field of in machine learning and natural language processing with a fixed-term contract of 12 months. You will take part in the SafeFood4ClimDiet research project coordinated by ANSES, in collaboration with the French National Research Institute for Agriculture, Food and the Environment (INRAE). This project aims at identifying the microbiological risks associated with new food practices influenced by climate change. In particular, it seeks to identify these emerging food practices through the development of natural language processing methods.
Within ANSES’s Risk Assessment Direction (DER), the Food Risk Assessment Unit (UERALIM) coordinates this project which is funded by the by the French National Research Agency (ANR).
Your main missions:
You will aim to develop an original Named Entity Recognition (NER) method in French and English, operating in zero-shot learning setting, i.e. without the need for manually annotated training data. The proposed approach will rely on large language models (LLMs) in “hard prompting” mode, taking advantage of the latent knowledge acquired during their pre-training on large-scale text corpora. The method will be evaluated on standard named entity recognition benchmark datasets (such as NCBI Disease Corpus, FoodBase corpus), and optimised to identify at least two specific types of entities: environmental concepts (e.g. "carbon footprint", "biodiversity loss", "environmental concern") and those related to food consumption behaviors (e.g. names of food like "apple", production methods such as "organic food" or sustainable practices like "composting food waste")
What kind of profile are we looking for?
PhD in Computer Science, Natural Language Processing (NLP), Text Mining or related discipline.
A first experience in one or more of the above-mentioned tasks would be appreciated
Languages ENGLISH Level Excellent
Languages FRENCH Level Excellent
Working with us means:
Contributing on a daily basis to our team and our commitments. And benefiting from: a dynamic skills development policy; 12 days' teleworking per month (subject to conditions); various benefits (administrative restaurant, RTT ie reduction of working hours, activities offered via the staff association).
Additional comments
Starting date:As soon as possible
Remuneration: Depending on experience and level of training, with reference to health agency pay scales.
Special conditions:
In accordance with Art L.5323-4 of the French Public Health Code, the person recruited will be required to complete a public declaration of interests.
Job category: Category 2 contract agentor category A permanent agent.