This postdoctoral position is part of the 2FAST project (Federation of Fluidic Autonomous labs to Speed-up material Tailoring). It focuses on accelerating chemical synthesis through continuous and miniaturized methods like microfluidics and flow chemistry. These techniques offer precise control over experimental conditions and leverage digital advancements for improved research outcomes in material chemistry. By utilizing databases, A.I., and real-time measurements, synthesis routes can be optimized, although the comprehensive characterization of nano/micro-materials remains challenging due to cost and complexity. Despite the lack of a universal approach to continuous chemical processes, the project aims to exploit digitalization in microfluidics laboratories, collaborating with experts in chip’s design and analytical techniques. Together, we will develop interoperable microfluidic chips to control material properties during synthesis. The postdoctoral project will focus on the orchestration aspect of the autonomous lab-on-a-chip. The main tasks will be:
• Designing, creating and evaluating feedback loops thanks to active learning models enabling to build correlations between control parameters (e.g. concentration of a reagent) and the collected signals (UV-Vis spectrum). At least, two feedback loops will be developed and compared, one based on classical optimization approaches, one based on reinforcement-based machine learning methods.
• Take part in the creation of a signal database adapted to machine learning methods particularly on the implementation of auto-encoder networks (e.g. GANs) to simulate signals and/or format the database.
• Implementing machine learning methods to connect "highly resolved data" to more readily available observables, and demonstrate the possibility to connect, desired nanoparticle properties and synthesis conditions.
• Managing interactions within the interdisciplinary team and also with external collaborations for A.I. implementation.
• Articles and reports writing

'2FAST is one of the targeted projects of the PEPR (Priority Research Programs and Equipment) project DIADEM. DIADEM is a comprehensive initiative aimed at accelerating the design and manufacturing of more efficient and sustainable materials. The appointed researcher will join an excellence network comprising four different laboratories at the national level: ICMCB (UMR5026) and LOF (UMR5258) in Bordeaux, LGC (UMR5503) in Toulouse, ISEC (CEA) in Marcoule, and LIONS (UMR 3685) in Paris Saclay.

Bac + 8

Doctorat

Spécialités : A.I or related fields : A.I., Machine learning, Microfluidic, programming, numerical silumation

Programming languages : Pytho, C++