PhD student in AI reliability
I work on the reliability of deep neural networks under hardware-like faults, with a focus on software-implemented fault injection, modern vision models, and efficient evaluation methodologies. I am also interested in mechanistic interpretability: studying how models represent, process, and use information, and how those internal mechanisms affect safety.
My current PhD work studies how deep neural networks behave when affected by hardware-like faults, and how to evaluate these effects with scalable software-based fault-injection workflows. I am also interested in mechanistic interpretability and model safety, especially how understanding internal model behavior can help make AI systems more reliable.
2025 - Present
Research focus: reliability of deep neural networks under hardware-like faults using software-implemented fault injection, with applications to modern vision models and efficient fault-injection methodologies. I am also building an interest in mechanistic interpretability: how models think, what internal structures drive their decisions, and how this connects to safety.
Winter–spring Planned · 3 months
A planned three-month research visit to work on iterative fault injection for neural networks and efficient reliability evaluation.
Spring–summer Planned · 3 months
A planned three-month research visit on the reliability of AI systems as a whole, with a real-world robotics use case involving TIAGo robots.
Training across artificial intelligence, computer vision, control, electrical engineering, and electronics.
2024 - 2025
2020 - 2025
First two years in EURINSA, studying in English, German, and French.
2026 Accepted · ICCAD 2026
TreeFI uses regression trees to group neural-network values by their response to bit flips and allocate fault injections where they matter most. Across the evaluated models, it reduces the required injection budget by up to 72.1× while preserving the target confidence and error margin.
2026–2027 · First semester Currently teaching
Tutorials and practical labs. Linux and shell scripting, C programming, pointers and dynamic memory, with compilation and debugging tools including make, GDB, and Valgrind.
2026–2027 · First semester Currently teaching
Tutorials and practical labs. Formal foundations of computer science: logic, sets and relations, inductive structures, formal languages, grammars, and finite automata.
Outside research, I like keeping a few things in motion.