Research Scientist, Machine Learning
QuantIA · Madrid, ES
Mar 2026 – present
I am a Research Scientist at QuantIA and Research Associate at the University of Bristol. My work specialises in developing structure-preserving machine learning models for systems with invariants, symmetries, and thermodynamic constraints. My PhD, supervised by Dr. Andrew Lawrie at the University of Bristol and funded by the National Nuclear Laboratory (NNL) and the Nuclear Decommissioning Authority (NDA), focused on model reduction and inference for high-dimensional dynamical systems.
Current positions
Research Associate, Machine Learning
University of Bristol · Bristol, UK
Apr 2026 – present
Research interests
My work sits at the intersection of machine learning, applied mathematics, and physical modelling—focused on learning models that respect the structure of the systems they describe.
- Structure-preserving machine learning: encoding invariants, symmetries, and geometric constraints into parametric models
- Spectral methods and Koopman operator theory for data-driven analysis and prediction of nonlinear dynamical systems
- Thermodynamically consistent reduced-order modelling via the Mori–Zwanzig formalism and stochastic coarse-graining
- Data-driven symmetry detection and equivariant architectures