LLM-Assisted Generation of Functional and Formal Hardware Models
Modern hardware systems, such as RISC-V processors and hardware accelerators, rely on functional simulators and formal verification models to ensure correct, reliable, and secure operation. Today, these models are mostly developed manually from design specifications, which is time-consuming and increasingly difficult as hardware architectures become more complex.
This PhD proposes to explore how Large Language Models (LLMs) can be used to assist the automatic generation of functional and formal hardware models from design specifications. The work will focus on defining a methodology that produces consistent and executable models while increasing confidence in their correctness. To achieve this, the approach will combine LLM-based generation with feedback from simulation and formal verification tools, possibly using reinforcement learning to refine the generation process.
The expected outcomes include a significant reduction in manual modeling effort, improved consistency between functional and formal models, and experimental validation on realistic hardware case studies, particularly RISC-V architectures and hardware accelerators.
Study of the Metastability of Silicon Heterojunction Solar Cells and Stabilization Strategies
Silicon-based photovoltaic cells, particularly silicon heterojunction (SHJ) cells using hydrogenated amorphous silicon (a-Si:H), achieve efficiencies exceeding 25%. However, these architectures exhibit intrinsic metastability, such as Staebler-Wronski degradation, which can lead to efficiency losses during storage between fabrication and module assembly. In the context of globalized supply chains, these instabilities represent an economic and technical risk that is not yet well quantified. This thesis aims to address the following questions: what is the quantitative impact of instability on the efficiency of high-efficiency cells during prolonged storage? What are the physical mechanisms responsible for this degradation? What technological strategies can reduce or eliminate this instability? What are the industrial implications for module logistics? To achieve this, a rigorous experimental protocol will be implemented to monitor the electrical performance of cells over several months under varying storage conditions (atmosphere, temperature, humidity). Test structures and advanced characterizations (FTIR, Raman, Silvaco TCAD) will be used to understand the underlying physical phenomena. Process optimization, introduction of new materials, and improved packaging will be explored to stabilize the cells. Practical recommendations for the industry, regarding maximum storage durations and optimal storage conditions, will also be established. The goal is to develop technological and logistical solutions to minimize efficiency losses in SHJ cells, optimize supply chains, and reduce associated economic risks.
Few-shot event and complex relation extraction from text applied to scientific literature
Information extraction from text, which falls under the broader field of Natural Language Processing, has been the subject of research for many years. These efforts have primarily focused on Named Entity Recognition, relation extraction between entities, and, in its most complex form, event extraction, a task typically formulated as filling predefined templates from unstructured text. Within this framework, the objective of this thesis is to design, develop, and evaluate event extraction models operating on scientific articles. In this context, an "event" may correspond to a set of entities and relations characterizing, for instance, a chemical reaction or an experiment. Furthermore, these models must be capable of being defined from a highly restricted set of annotated data to allow for rapid adaptation to new scientific domains.
From a methodological standpoint, the proposed thesis seeks to move beyond the current, almost reflexive tendency to rely exclusively on Large Language Models (LLMs). Instead, it advocates for a potential synergy between LLMs and smaller encoder-based models within a few-shot context. In this synergy, the former are leveraged, through the generation of synthetic data and annotations, to build the resources necessary to implement the latter via pre-training mechanisms. This thesis will be conducted within the framework of the AIKO project of the Digital Programs Agency, which focuses on knowledge extraction from scientific publications.
Architecture of small animal single photon emission tomograph.
Medical imaging, a source of major innovations, presents remarkable potential for meeting new challenges with the growing demand for precision medicine, which requires cutting-edge diagnostic and therapeutic approaches personalized for each patient.
In this context, CEA-Leti proposes a PhD internship to develop a dedicated preclinical SPECT (Single Photon Emission Tomography) imager that will provide the performance (spectral information, high resolution, and high sensitivity) needed by researchers developing new radiopharmaceuticals.
The laboratory has a recognized expertise on CZT (Cadmium Zinc Telluride) semiconductor imagers enabling better spatial and energy resolution than scintillators used by most systems. They open new opportunities for emission imaging like easier Compton imaging, multi-isotope imaging and better contrast.
The candidate will have to handle the following tasks:
1. Study the state of the art of small animal SPECT imagers to participate with the team to the choice of system specification and choice of a draft architecture.
2. Simulate this architecture by using Monte-Carlo codes and optimize free parameters.
3. Design and manufacture the prototype system, with the help of the team including system engineers.
4. Test and validate the imaging capabilities, using reconstruction algorithms provided by the team.
The PhD will be conducted inside an instrumentation laboratory with access to acquisition electronics, detectors, motorized mechanics, gamma-ray sources and processing/simulation software. The candidate will also work in collaboration with a clinical and preclinical centre (at Orsay’s hospital) for conducting imaging test on phantoms and animals.
Sustainable development of digital circuits and systems: Taking planetary boundaries into account
Technological developments in the electronics sector are experiencing rapid growth, accompanied by increasing interest in accounting for their environmental impacts. However, current approaches remain largely focused on relative impact reductions (energy efficiency, resource optimization), without ensuring compatibility with planetary boundaries. In this context, the concept of absolute sustainability emerges as an essential framework for guiding future developments of electronic systems.
This PhD thesis addresses several major scientific challenges: how can carrying capacities and sharing principles (core concepts of absolute sustainability) be identified for the electronics sector and consistently translated down to the levels of digital systems and integrated circuits? How can planetary boundaries be concretely integrated into the design of systems and circuits?
The main objective of the thesis is to move from a logic of relative environmental impact reduction toward designs that are compatible with planetary boundaries. It aims to define socio-technical scenarios to identify sharing principles, to conduct the first absolute life cycle assessment of a digital system, and to propose the first design of a circuit based on absolute limits, paving the way for sustainable development in electronics.
Controlling the composition and microstructure to achieve high magnetic performance in 1–12 rare earth-poor magnets
Permanent magnets based on rare earth elements (REEs), particularly neodymium-iron-boron (Nd-Fe-B) magnets, are strategically important for the development of more efficient motors and generators (electric vehicles, wind turbines). However, REEs, particularly Nd, are critical materials, with a high risk of supply disruption in the coming years. The growing demand for high-performance magnets requires the development of new types of magnets with reduce RE content. Iron-rich compounds, such as Sm-Fe12 (commonly known as phase 1-12), have very interesting intrinsic magnetic properties and are considered the best alternative to NdFeB magnets, allowing for a TR saving of around 35% by weight. However, achieving sufficient magnetic performance (remanence > 1 T and coercivity > 800 kA/m) depends on obtaining a suitable microstructure and remains the main challenge in the development of Sm-Fe12 magnets.
The aim of the thesis is therefore to improve the magnetic performance of this new family of magnets, in particular by controlling the composition and distribution of phases at grain boundaries. The doctoral work will combine an advanced experimental approach (development of Sm-Fe12 alloys, characterization of equilibrium phases, magnet manufacturing, magnetic characterization) with knowledge of phase diagrams to define compositions and optimal manufacturing conditions to achieve the targeted magnetic performances.
Model-Driven DevOps for Cloud Orchestration : Bridging Design-Time and Runtime Guarantees
Model-Driven Engineering (MDE) has traditionally relied on a clear separation between design and runtime, but this boundary no longer holds in today's cloud-native and edge environments, where infrastructures are heterogeneous, dynamic, and continuously evolving. Assumptions validated at design time may become invalid during execution, and modern orchestration platforms such as Kubernetes or OpenStack, while effective, remain weakly connected to architectural modeling environments. This results in a structural gap between architectural specification and actual operational behavior. To bridge this gap, this thesis proposes to develop a formal modeling framework for placement constraints across heterogeneous orchestration platforms, ensuring continuity between design-time validation and runtime guarantees. This framework would elevate placement constraints — resource locality, affinity, network latency, security isolation, and quality-of-service objectives — to first-class modeling constructs. At design time, it would enable static feasibility analysis and automated generation of deployment artifacts; at runtime, it would ensure continuous compliance monitoring and adaptive reconfiguration in response to violations. Expected contributions include a formal modeling language, bidirectional transformations between design-time models and runtime representations, and integration with Papyrus-based tooling. The ultimate goal is to ensure that architectural intent remains consistent and verifiable throughout the entire system lifecycle, from initial design through to production operation.
Non-invasively exploring the cerebellum microstructure with magnetic resonance
To better diagnose and monitor brain diseases, we need “non-invasive biopsies” to access the tissue cell-type composition and state without opening the skull. Magnetic resonance imaging (MRI) research efforts attempt to tackle the challenge but often lack cellular specificity because of the ubiquitous nature of water. Diffusion-weighted magnetic resonance imaging (dMRS) measures diffusion of intracellular and partly cell specific molecules in a region of interest, and forms a solid basis for resolving cell-types non-invasively. Among challenges, resolving signal contributions from the different cerebellar neurons could help monitor and understand neurodevelopmental and ataxic disorders. The cerebellum is a brain region representing 10% of the brain volume but containing more than half of the brain neurons, with the very large and complex Purkinje cells and the very small and round granule cells, both having very different functions and metabolism. The PhD project aims to disentangle these cells with complementary strategies: a classical dMRS approach and a quantum dMRS approach confronted to the state-of-the-art microstructure MRI methods.
Topologically Isolated Mode Acoustic Resonators
Timing is a key function in electronic circuits. Beyond on-chip signals synchronization, it also allows the synchronization of wireless data transmissions. Accurate time references require stable frequency sources, which also benefit to sensor applications. The gold standard for time or frequency generation is still quartz resonators, which are however bulky and difficult to miniaturize. Research is therefore still ongoing to provide high quality factor (> 10,000) resonators, ideally capable of operating at frequencies of several GHz. A key to reach such high quality factors is to confine strongly the mechanical vibration of micro-size structures in order to make them insensitive to external perturbations. Recently, the field of topological acoustics has demonstrated the capability to confine elastic waves in very small volumes concentrated at the interface between periodic structure, and to provide extremely high quality factor resonances.
This PhD position focuses on exploiting topologically protected modes in piezoelectric microstructures to provide next generations of high quality factor resonators, which may be used in oscillators or even filter circuits. Leveraging the know-how of CEA Leti in the design and fabrication of such components, the PhD will be part of an international collaboration with well established academic laboratories (Politecnico di Milano, Imperial College FEMTO-ST Institute) and industrial partners.
The candidate will model and design structures supporting topologically protected modes, combinining finite element simulations with simplified numerical approaches which reduce computation times. He will follow the fabrication of demonstrators in collaboration with the process integration teams in the CEA Leti clean rooms, and carry on measurements of the proposed resonators.
Distributed multimodal learning for cooperative acoustic source localization and classification
In many complex environments, such as industrial sites, disaster-stricken buildings, or public spaces, it is necessary to automatically detect and localize sound events (falls, alarms, voices, mechanical failures). Mobile platforms equipped with cameras and microphones represent a promising solution, but a single platform remains limited: its microphone array provides an approximate direction towards the source but not a precise position in space, and its camera may be obstructed. This thesis proposes to study how a network of mobile platform, each carrying a calibrated audio-visual unit, can collaborate to localize and classify such events in 3D. Each platform analyses its own audio-visual observations and shares an estimate of the source direction with its neighbours; the network then combines these estimates to reconstruct the position of the event and identify it. The expected outcomes are a cooperative localization system that is robust to occlusions and partial platform failures.