AI-Driven Design & Optimization of Load-Modulated PAs for 6G Applications
The proposed PhD research focuses on the AI-driven design and optimization of load-modulated power amplifiers (PAs) for next-generation 6G wireless systems, where extreme data rates, energy efficiency, and linearity are paramount. The study aims to integrate machine learning and evolutionary optimization techniques into the PA design flow to enable intelligent trade-offs between efficiency, bandwidth, and linearity under dynamic load modulation. Physics-based circuit modeling will be coupled with surrogate modeling and reinforcement learning to explore vast design spaces with reduced computational cost. Emphasis will be placed on real-time load modulation architectures (e.g., Doherty, Outphasing, and hybrid topologies) implemented in advanced semiconductor technologies such as GaN and InP. The project further seeks to establish AI-guided co-optimization frameworks linking device-level characteristics with system-level performance. Expected outcomes include novel design methodologies, compact behavioral models, and experimentally validated prototypes demonstrating high efficiency across wide modulation bandwidths, paving the way toward sustainable, adaptive, and intelligent 6G RF front-ends.
Impact of ultrasound on the flow properties of complex suspensions
Nuclear industry generates radioactive wastes of various nature such as solids, liquids but also sludges coming from effluent treatment facilities or historical residues stored in pool or tanks. The physico-chemical nature of those sludges leads to a complex flow behaviour making it difficult to handle and convey prior their immobilization in a conditioning matrix. In order to fluidize these suspensions of varying compositions, the mechanical action of power ultrasound is envisaged. It has recently been shown, thanks to a set-up coupling power ultrasound and rheology, that it is possible to significantly reduce the yield stress and viscosity of the slurry by applying ultrasound. The aim of this thesis is to pursue the studies already undertaken (physical chemistry, microstructure, ultrasound and rheology) on reconstituted sludge or simplified model suspensions, focusing more specifically on two aspects. The first, more fundamental, will aim to gain a better understanding of the interaction between power ultrasound and matter, with a particular focus on the origin of the effects observed (interfaces vs. volume). The second aspect will be more applied, with the development of original larger-scale experimental devices capable of generating flows closer to industrial situations. For this phD work, we are looking for a motivated, serious and curious candidate. Given the multidisciplinary character of the subject, mixing physics, physico-Chemistry and experimental development, the candidate could valorize his new skills in various industrial fields such as nuclear, civil engineering and depollution domain.
The thesis will be conducted in a laboratory at CEA Marcoule, which provides the scientific, technical, and human resources necessary to carry out the research. Short stays are planned at the physics laboratory of ENS Lyon. This PhD topic, combining both fundamental understanding and applied aspects, offers dual career prospects: either pursuing a postdoctoral position or entering a career in industry.
On the fluid distribution for liquid thermocline - From experimental work to reduction of models
Thermocline heat storage (stratified tank) is an industrial solution for recovering waste heat and integrating intermittent energy sources. However, its performance remains limited by poorly controlled phenomena: non-uniform fluid distribution, partial thermal cycling, and real-world operating conditions (fluctuating inputs, incomplete cycles).
The proposed doctoral research builds upon the PhD work of Alexis Ferré and the postdoctoral research of Martin Rudkiewicz, which focused on the modeling and characterization of thermocline storage systems. These studies led to the development and validation of a comprehensive physical model implemented in ANSYS Fluent, enabling detailed investigation of the physical phenomena governing the formation and subsequent transport of the thermocline within a storage tank.
A partially validated CFD numerical model, together with a fully operational experimental facility, will therefore constitute the foundation of this PhD project. The main objectives are:
• to further advance the experimental characterization of liquid thermocline storage behavior, with particular emphasis on the influence of flow distribution (including distributor type and design parameters), thermal cycling, and initial conditions on storage performance;
• to validate the CFD physical model against newly acquired experimental data;
• to reduce the high-fidelity CFD model to a comprehensive system-level model incorporating the distributor, the storage tank, and the extraction process;
• to provide the scientific and industrial communities with currently unavailable datasets that are essential for model validation under varied and realistic operating conditions.
Low Power Image Sensor for Distributed Processing in Cameras Network
Working in a collaborative academic project, your task will be to develop a smart image sensor for a wireless camera network embedding distributed AI computing.
Current camera network contains several standard cameras that transmit their images to a global server performing the targeted inference processing. This kind of architecture proposes energy and frugality performances that are not compatible with IoT requirements.
The project goal is to tackle hardware frugality through a distributed and collaborative approach based on ultra-low-power computing nodes. Each node’s inference core will be built around ASIC processors performing calculations in analog form. The final demonstrator will consist of a wireless network of “motes” (sensor network nodes) integrating dedicated image sensors paired with hybrid processors performing analog processing.
In this context, the mote’s image sensor must extract strategic features with frugality and efficiency which implies that you have to define, design and test an innovative readout architecture of a standard imager. In collaboration with the academic partners, you will be involved in the definition of the overall mote architecture allowing to define basically the output data format and the output procedure of the imager including potential pre-processing for the distributed inference computations. The studied architecture will integrate innovative low power solutions to address the targeted IoT applications and perform both image acquisitions and AI pre-processing.
As an image sensor demonstrator is planned in this PhD Thesis, the work will be conducted at CEA-Leti in the L3i Laboratory, using professional IC design tools and software development environments.
Post-training neural architecture optimization for small language models
Generative AI, and particularly language models (LLM), have sparked a new revolution in AI with applications across all domains. However, LLMs are highly resource-intensive and, hence, difficult to implement on autonomous embedded systems. LLMs can be optimized by modifying their architecture to replace heavy Transformer layers with lighter alternatives. Given the difficulty of training LLM "from scratch," this thesis aims to develop post-training neural architecture optimization methods applicable to small LLM (SLM). Additionally, the thesis seeks to propose performance metrics of different layers of an SLM and their alternatives, to guide the replacement, and thus propose a comprehensive methodology for optimizing SLMs while considering hardware constraints. The work will be valorized through publications in major AI conferences and journals, and the developed codes and methods could be integrated into the tools developed at CEA.
Contribution in the study of Power Partial Converters in Energy sources Hybridization
One of the key areas for reducing the carbon footprint is transport, particularly the development of electric mobility, which is currently growing rapidly. In this context, the hybrid electric transport market is growing. Hybridization applications have seen their power increase and with it that of power electronics converters allowing to adapt the voltage levels of energy sources and the energy exchanges between them. This increase in power is accompanied by higher losses to be evacuated, resulting in a significant impact firstly on the size of the converters, and therefore of the overall system, and then on the energy efficiency of the entire chain. Efforts have already been made at CEA-LITEN to develop high-efficiency DC-DC converters (in particular by using interleaved DC-DC converters). The objective of the thesis will be to go further by studying the so-called partial power converters (PPC). The different architectures/topologies will be studied for hybrid applications associating a fuel cell and a battery on the one hand, and applications associating 2 batteries (one power type battery and the other, energy type battery) on the other hand. The work aims to determine the best architecture/topologies for each of the typical applications allowing a significant reduction in the size of the converters and the improvement of the efficiency of the whole system
Control coordination of power converters on the distribution grid to enhance overal system stability
With the increasing number of generation and consumption units connected through power electronic converters, the electrical grid is evolving toward a more dynamic and decentralized structure. This transformation strengthens both the need and the potential for these converters to actively contribute to system flexibility and stability—particularly in compensating for renewable energy fluctuations and maintaining the balance between supply and demand.
Optimized coordination of their control functions offers significant potential to improve grid resilience, by intelligently leveraging their capabilities in voltage regulation, frequency support, and reactive power control. However, to integrate these contributions effectively at scale, it is essential to develop holistic modeling approaches that capture multi-scale interactions—both in time and space.
The modeling work in this thesis aims to represent the relationship between the active/reactive power flexibility of power electronic converters and the stability margin they provide to the grid, as well as to model the aggregation of their actions for system-wide contribution. Building on this foundation, coordinated control architectures and algorithms between the distribution and transmission networks will be investigated, developed, and validated.
Prediction of elastic wave dispersion effects using a semi-analytical model under high-frequency approximation
Ultrasonic testing (UT) methods are a fundamental component of non-destructive testing (NDT). They are widely used to inspect mechanical components such as welds (in nuclear and petrochemical industries) and composite material structures (in aeronautics). To understand the physical phenomena involved in a given configuration, simulation is a valuable tool and sometimes an essential step in implementing the inspection process.
Modeling approaches fall into two main categories: purely numerical models based on finite elements (FE) and semi-analytical methods derived from high-frequency (HF) approximations, such as paraxial rays. While the latter are often favored for their computational efficiency, they introduce simplifications that can compromise the quantitative accuracy of results, particularly for phenomena like dispersion (variation in wave speed with frequency), which are common in certain industrial contexts.
This thesis project aims to enhance the paraxial ray approach by integrating models of dispersive interfaces (composite interplies, coupling layers), dispersive viscoelastic media, and a modal guided wave model. The goal is to develop a simulation tool capable of faithfully reproducing realistic inspection configurations, thereby improving the representativeness of the results.
Reconciling predictability and performance in processor architectures for critical systems
Critical systems have both functional and timing requirements, the latter ensuring that deadlines are always met during operation; failure to do so may lead to catastrophic consequences. The critical nature of such systems demands specialized hardware and software solutions. This PhD thesis topic focuses on the development of computer architecture designs for critical systems, known as predictable architectures, capable of providing the necessary timing guarantees. Several such architectures exist, typically based on in-order pipelines and incorporating behavioral restrictions (e.g., disabling complex speculation mechanisms) or structural specializations (e.g., redesigned caches or deterministic arbitration for shared resources). These restrictions and specializations inevitably impact performance, and the design of predictable architectures must therefore address the predictability–performance tradeoff directly. This PhD thesis aims to explore this tradeoff in a novel way, by adapting a high-performance variant of an in-order processor (CVA6) and developing top-down techniques to make it predictable. Performance in such processors is usually achieved through mechanisms like branch prediction, prefetching, and value prediction, implemented via specialized storage elements (e.g., buffers) and supported by control mechanisms such as rollback on misprediction. Within this context, the goal of the thesis is to define a general predictability scheme for speculative execution, covering both storage organization and rollback behavior.
Out-of-Distribution Detection with Vision Foundation Models and Post-hoc Methods
The thesis focuses on improving the reliability of deep learning models, particularly in detecting out-of-distribution (OoD) samples, which are data points that differ from the training data and can lead to incorrect predictions. This is especially important in critical fields like healthcare and autonomous vehicles, where errors can have serious consequences. The research leverages vision foundation models (VFMs) like CLIP and DINO, which have revolutionized computer vision by enabling learning from limited data. The proposed work aims to develop methods that maintain the robustness of these models during fine-tuning, ensuring they can still effectively detect OoD samples. Additionally, the thesis will explore solutions for handling changing data distributions over time, a common challenge in real-world applications. The expected results include new techniques for OoD detection and adaptive methods for dynamic environments, ultimately enhancing the safety and reliability of AI systems in practical scenarios.