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

UMR ITAP (Technologies and Methods for the Agriculture of Tomorrow joint research unit) has about 80 people, including 35 permanent members, divided into 4 teams. It conducts research on the environmental metrology chain, covering all stages of the “measure-understand- decide-act” chain. Its work covers a range of scales, from the plant to the plot, from the farm to the territory, to help define the efficient, sustainable agriculture of tomorrow.
You will be positioned within the DeMo team (Decision-making and Modelling with Agri-environmental data, 11 members) working on spatial and temporal agricultural data processing methods for operational decision support for the management and characterisation of agroecosystems. The work is largely applied to the field of precision agriculture, and increasingly to digital agriculture applications.
The processing of data from digital agriculture represents a major challenge in supporting the transition of agriculture; from a finalized point of view, to meet the monitoring and intervention needs of professionals on agro-systems at different spatial scales, but also from a theoretical point of view, to address the specificities linked to digital agriculture data (multimodal, heterotopic, asynchronous, uncertain, incomplete, etc.) for operational use in agriculture.
UMR ITAP is at the forefront of research in both these areas. In particular, it has contributed to the development of original approaches to Spatial Data Processing for Precision Agriculture, integrating geostatistics with operational intervention constraints (machines, human resources), as well as chemometrics and machine learning for processing multivariate data, mainly spectral and hyperspectral.
Processing these data for decision support requires the integration of new approaches to address their specificities, and first and foremost the multimodal aspect, in a context where: i) qualified datasets (ground truth) are small (a few dozen) compared with available observations, ii) model interpretability is necessary to better understand and exploit the potential of available observations, but also to validate the relevance of the model, iii) there is great variability in pedo-climatic contexts, which raises the question of the specialization of decision-support models and their transfer.
In this context, you will be charged with devising or adapting data mining methods:
- through multimodal data aggregation approaches, supervised or unsupervised, integrating the specific context of digital agriculture.
- by jointly exploiting the spatial and temporal character of these structurally complex data.
- more broadly, you will propose methods for transferring knowledge (transfer learning) to new pedo-climatic situations in a context of scarce field data and available expertise.

You will benefit from the wide collaboration network already existing in ITAP and you will expand it in different directions. You will participate in ongoing projects and develop your own ones to propose processing methods adapted to these structurally complex data.

Training and skills

You hold a PhD degree or equivalent. Specialisation in data science (statistics, data analysis, machine learning, etc.) and dual skills in agronomy are highly recommended.
You have a solid knowledge of mathematical concepts related to multivariate data analysis. Skills in statistics applied to biological phenomena, and deep understanding of the spatial and temporal variability of natural or anthropized systems are desired. An interest in applied research and targeted applications is recommended. The ability to discuss and collaborate with specialists in applied disciplines is expected.
You enjoy teamwork and you have good interpersonal skills. You show initiative, autonomy and dynamism.
Fluency in English is desirable, as is long-term international experience: successful candidates who have not already had such experience will be encouraged to spend a period abroad, co-designed with the host team, at the end of the 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 Application guidelines CRCN 2025 pdf - 3.93 MB
2. I write down the profile number CR-2025-MATHNUM-3
3. I apply GO