The French National Research Institute for Agriculture, Food, and the Environment (INRAE) is a public research establishment under the dual authority of the Ministry of Agriculture and the Ministry of Research.
INRAE is recruiting researchers by open competition and offering permanent position.
It is a major player in research and innovation created on 1st of January 2020. INRAE is a research institute resulting from the merger of INRA and IRSTEA. It is a community of 12,000 people with more than 200 research units and 42 experimental units located throughout France.
The institute is among the world leaders in agricultural and food sciences, in plant and animal sciences, and is 11th in the world in ecology and environment. INRAE’s main goal is to be a key player in the transitions necessary to address major global challenges. In the face of the increase in population, climate change, scarcity of resources and decline in biodiversity, the institute develops solutions for multiperformance agriculture, high quality food and sustainable management of resources and ecosystems.
Work environment, missions and activities
The “Mathématiques et Informatique appliquées de Toulouse (MIAT)” research unit is part of the MathNum research department of INRAE. It comprises of two research teams (SCIDYn and SAaB) and three support teams (platforms GENOTOUL Bioinfo, RECORD and SIGENAE).
The candidate will be part of the SCIDyn team that includes 13 computer and statistics scientists and engineers.
The core activities of the SCIDyn team lie in the design of agroecosystems simulation models and their use in computer experiments to design innovative agricultural systems. The team is well-known for its work on controlled agroecosystems’ simulation and design-through-optimisation of control strategies. You will strengthen the team in the reinforcement-learning domain, in order to move away from the classical dilemma: simplistic model optimisation or finding a "good" solution amongst a set of strategies evaluated by simulations. You will lead original researches in reinforcement-learning, domain that is usually in the Artificial Intelligence discipline but is also explored in Statistics (meta-modelling) or in Operational Research (simulation-optimisation community). One of the main deadlocks of the discipline is reinforcement-learning with complex models, typically highly dimensional ones. This challenge is currently tackled using approaches such as “Bayesian Reinforcement Learning”, “Deep Reinforcement Learning”,... which you might explore. Your research will help deal more efficiently with issues such as ecosystem decision-making at a landscape scale, ecosystems trade-offs between services by exploring already existing simulation models or real-time crop management, including complex “plant-level” models and integrating online data acquisition data from sensors.
Training and skills
Candidates must have a PhD or equivalent.
A PhD in artificial intelligence, statistics or operational research would be appreciated. Skills in reinforcement learning, or simulation optimization for decision making would be appreciated too.
An interest for applications-oriented research would be welcome. The thematic field of research for the position is agroecology but a candidate with an experience in other application in other domains with similar approaches is possible. A good level in English language and a significant research experience abroad are a prerequisite: in the case of an absence of such experience, the recruited person will have to undertake a research sojourn abroad after her definitive recruitment.
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.