Scientific direction Development of key enabling technologies
Transfer of knowledge to industry

PostDocs : selection by topics

See all positions

Evaluation of RF system power consumption for joint system-technology optimization

Département Systèmes (LETI)

Laboratoire Architectures Intégrées Radiofréquences



To be able to increase and optimize wireless transmission systems based on a hybridization of technologies, it is strategic to be able to quickly evaluate the capabilities of these technologies and to adapt the associated architecture as best as possible. To this end, it is necessary to implement new approaches to global power management and optimization. The work of this post-doctoral contract is at this level. The first step will be to develop some new power consumption models of the RF transceivers building blocks (LNA, Mixer, Filter, PA, ?). A modelization approach has already been tested and validated in the group. In the next step, it will be needed to link the performances of the overall wireless system to the building blocks characteristics. Lastly, the optimization will be applied thanks to an efficient solution. Lastly, the proposed approach will be validated in the optimisation of a multi-antenna millimeter wave wireless system. An evaluation methodology specific to 3D will also be put in place

Download the offer (.zip)

High precision robotic manipulation with reinforcement learning and Sim2Real

Département Intelligence Ambiante et Systèmes Interactifs (LIST)

Laboratoire Vision et Apprentissage pour l'analyse de scènes



High precision robotic assembly that handles high product variability is a key part of an agile and a flexible manufacturing automation system. To date however, most of the existing systems are difficult to scale with product variability since they need precise models of the environment dynamics in order to be efficient. This information is not always easy to get. Reinforcement learning based methods can be of interest in this situation. They do not rely on the environment dynamics and only need sample data from the system to learn a new manipulation skill. The main caveat is the efficiency of the data generation process. In this post-doc, we propose to investigate the use of reinforcement learning based algorithms to solve high precision robotic assembly tasks. To handle the problem of sample generation we leverage the use of simulators and adopt a sim2real approach. The goal is to build a system than can solve tasks such as those proposed in the World Robot Challenge and tasks that the CEA's industrial partners will provide.

Download the offer (.zip)

Fibre optic sensor instrumentation for thermomechanical measurements in harsh environment

Département Métrologie Instrumentation et Information (LIST)

Laboratoire Capteurs Fibres Optiques



In connection with the people in charge of the project in the LCFO laboratory (DRT Saclay) and the LMES laboratory (DAM Cesta), the postdoctoral fellow will participate in the development of the on-board interrogation system, from both a system and an algorithmic point of view, as well as in the development of the fibre optic sensor test on the SPRITE installation. The person recruited will also be in contact with the LRP laboratory (DAM Le Ripault) in order to participate in tests of fibre integration within plasma-sprayed ceramics. He or she will carry out measurements of the spectral quality of the integrated sensor and will analyse these spectra once the integration has been carried out but also during the integration. The person recruited will be based mainly on the Saclay site but will be required to travel for a few days to the CEA Cesta and CEA Le Ripault sites in order to set up and carry out the experiments. Skills in optics, instrumentation, embedded systems and algorithms are required.

Download the offer (.zip)

Development of combined cathodoluminescence and photosensitive Kelvin probe force microscopy protocol for LED applications

Département des Plateformes Technologiques (LETI)

Laboratoire Analyses de Surfaces et Interfaces



During this post-doc fellowship, the applicant will be involved in development of very innovative characterisation techniques. More specifically: (1) CL mapping will be compared with KPFM photovoltage mapping on different types of materials (GaN and InGaN) to see the impact of defects (e.g. dislocations, V-pits, etc.) on measured signals. Analysis protocol will be developed to properly compare the KPFM and CL measurement, (2) the protocol of sample preparation will be developed to mark the sample on desired area. This preparation will allow to perform the both characterization techniques within the same sample area and will allow to analyze the proportion of radiative and non-radiative recombinations on defects, (3) pump-probe KPFM will be tested to obtain recombination time of non-radiative process. The applicant must be strongly motivated to learn how to handle advanced UHV facilities and analyse the data. He will have the opportunity to develop transverse skills as the work will be carried out with academic collaborators, and will involve issues of intellectual property, industrial experience with the LETI partners and a daily practise of the English language. Proper background in solid-state physics is essential. Basic knowledge about scanning probe microscopy or/and luminescence techniques is not mandatory but will be appreciated.

Download the offer (.zip)

Development of decentralized and resilient algorithms for federated learning

Département Métrologie Instrumentation et Information (LIST)

Laboratoire Intelligence Artificielle et Apprentissage Automatique



The postdoctoral fellow will join the FANTASTYC project (internal to CEA) which puts together researchers on distributed ledger technology, privacy and machine learning with the aim of developing software assets for decentralized, privacy-preserving and resilient federated learning. In more detail, the first objective of this fellowship is to envisage a fully decentralized efficient version of the federated learning, replacing communication with the server by peer-to-peer communication between individual clients on some communication graph. On doing that, the postdoctoral fellow is expected to tackle some of the open challenges involved by passing to decentralized learning, including: (1) the design, specification and implementation of resource-aware decentralised learning protocols; and (2) tackling the compromise between generic and personalized models depending on the evaluated non-IID data distributions available to individual clients (e.g. different models for clusters of participants). The other focus of this position will be the study of the robustness of distributed federated learning against the presence of malicious participants (i.e. Byzantine attacks)

Download the offer (.zip)

Elaboration of a common robot/human action space





This post-doc aims at establishing by artificial intelligence methods (e.g. signal processing on graphs), the mapping of an industrial task performed by a human operator, and acquired by visual sensors, in order to be interpretable and exploitable by a robot. It is part of a project aiming at designing a demonstrator in which a robot will learn to reproduce by observation a task performed by a human. The platform has been deployed at CEA Tech and is currently operated by an engineer. The objective of this post-doc is mainly to study and develop a set of methods to build a mapping between the actions performed by a human operator and perceived through visual sensors and the actions performed by the robot. These methods and the work of the related theses will then be implemented in the demonstrator in order to test them experimentally. Due to the central position of the subject of this post-doc, under the triple supervision of the PACCE and IPI teams of LS2N and CEA, you will have to collaborate closely with the two PhD students already involved in the project. You will have to conceptualize and formalize the methods and representations on the one hand by synthesizing the existing literature on the subject and on the other hand by establishing a common framework encompassing the two thesis works.

Download the offer (.zip)

30 Results found (Page 4 of 5)
first   previous  1 - 2 - 3 - 4 - 5  next   last

See all positions