Junior research scientist in multimodal data science

Back to campaign's jobs listing

INRAE presentation

INRAE, the French National Research Institute for Agriculture, Food, and Environment, is a public research organization bringing together 12,000 employees across 272 units in 18 centers across France. As the world’s leading institute specializing in agriculture, food, and the environment, INRAE plays a key role in supporting the necessary transitions to address global challenges.

Faced with population growth, food security challenges, climate change, resource depletion, and biodiversity loss, INRAE is committed to developing scientific solutions and supporting the evolution of agricultural, food, and environmental practices.

INRAE is recruiting researchers by open competition and offering permanent position.

Work environment, missions and activities

You will carry out your research activity within the Joint Research Unit UMR ITAP (Technologies and Methods for Tomorrow’s Agriculture), which brings together around 80 people, including 35 permanent staff members, organized into four teams. The Unit conducts research along the entire environmental metrology chain, covering all stages from measurements to understanding, decision-making and action. You will be assigned to the DéMo team (Decision and Agro-environmental Modelling), composed of about 10 permanent scientists with diverse expertise (data science, modelling, computer science, digital agriculture). The team’s research mainly focuses on the analysis and use of multimodal data from digital agriculture. It develops methods for processing spatial and temporal agricultural data to support operational decision-making for the management and characterization of agroecosystems. You will collaborate closely with researchers from the COMiC team (Optical sensors for Complex media), who design optical sensors based on spectral measurements and develop associated data analysis methods.
The exploitation of data from digital agriculture technologies represents a major challenge for supporting the transition of Agriculture. Collected across various spatial and temporal scales and drawn from multiple sources (sensors, remote sensing, connected devices, expert knowledge, crowdsourcing), these data offer unprecedented opportunities to extract valuable information and feed decision-support systems aimed at characterizing and managing agricultural systems.
Achieving these objectives requires advanced data analysis methods capable of handling heterogeneous, noisy and incomplete data gathered under diverse agro-ecological conditions, while integrating expert knowledge and operational constraints.
Through a multidisciplinary approach, combining data science, spatio-temporal modelling and the integration of agronomic contexts, you will contribute to developing new methods tailored to technological evolutions and the challenges posed by the transition of Agriculture.
In this context, you will be responsible for designing, adapting and implementing data exploration methods that i) aggregate multimodal data, whether supervised or unsupervised, while integrating the specific context of digital agriculture, ii) jointly exploit the spatial and the temporal dimensions of structurally complex data, and iii) mobilize transfer-learning approaches to account for new pedo-climatic situations where filed data and expert knowledge are scarce.
Mobilizing these data for decision support requires developing original approaches adapted to their specificities, especially their multimodal characteristics, in a context where (i) high-quality, ground truth datasets are limited (tens of cases) compared to the number of observations available, (ii) model interpretability is essential to better understand and leverage the available observations and to validate model relevance and (iii) there is a high variability in pedo-climatic contexts, raising questions about the specialization and transferability of decision support models.
Within UMR ITAP, you will develop original methods for exploiting complex agricultural data to support decision-making and ensuring model interpretability ; design and implement the associated algorithms ; collaborate with researchers in data science and other disciplines (e.g. agronomy) ; monitor and contribute to the state of the art both at national and international levels in this rapidly evolving field.
The data science scientific community in Montpellier in highly dynamic (Université de Montpellier, INRIA, INRAE, CIRAD). You will actively participate in this ecosystem by establishing collaborations relevant to your research project. Within MathNum (Related scientific department if INRAE), you will interact particularly with scientists from UMR MISTEA (statistics, data science) and UMR TETIS (remote sensing, Machine Learning). You will also develop your own network of national and international collaborations, enhancing your research activities.You will participate in ongoing projects within the ITAP (for example TADAC Project, which focuses on developing methods for processing poorly structured historical data from diverse sources) and will be encouraged to initiate new research project aligned with your scientific objectives.

Training and skills

The position is open to candidates holding a PhD (or equivalent). A specialization in data science (statistics, data analysis, machine learning, etc.) is highly recommended. You should have a strong background in mathematics related to multivariate and spatio-temporal data analysis. Skills in applied statistics for biological processes, as well as knowledge of the spatial and temporal variability of natural and human-managed systems, are desirable. A dual background in agronomy would be an additional asset.
An interest in applied and mission-oriented research is recommended. The ability to interact and collaborate effectively with specialists from applied disciplines will be expected.
You should enjoy teamwork and demonstrate significant interpersonal skills. You are expected to show initiative, autonomy and enthusiasm in your work.
Proficiency in English is required and significant international experience is strongly encouraged. Successful candidates without prior long-term international experience will be expected to undertake an international research stay following their probationary year.

INRAE's life quality

By joining our teams, you benefit from:

- 30 days of annual leave + 15 days "Reduction of Working Time" (for a full time);
- parenting support: CESU childcare, leisure services;
- skills development systems: training, career advise;
- social support: advice and listening, social assistance and loans;
- holiday and leisure services: holiday vouchers, accommodation at preferential rates;
- sports and cultural activities;
- collective catering.

For international scientists: please visit your guide to facilitate your arrival and stay at INRAE. 

How to apply

1. I download the applicant guide Guide for applicants 2026 pdf - 1.41 MB
2. I write down the profile number CR26-MathNum-2
3. I apply GO