Geometric deep learning
Graph neural networks, node embeddings, and learned representations over meshes and point clouds, the structures that physical simulation actually lives on.
GNNsnode embeddingsmesh learningpoint clouds
01
About
I am an ML Research Engineer at Mercedes-AMG Petronas, working on applied machine learning and research engineering.
My research interests span geometric deep learning, spatial and physical AI, and robust learning. I will continue this work through a DPhil in Oxford's Visual Geometry Group.
02
Research interests
Spatial & physical AI
Learning representations that connect geometry, perception, and physical structure.
3D learningspatial reasoningphysical AI
Learning from imperfect data
Noisy labels, severe class imbalance, and the realities of scientific and security datasets, training models that hold up when the supervision doesn't.
noisy labelsimbalancesecurity MLmalware
03
Selected publications
04
Path
2026 →
DPhil candidate, Visual Geometry Group
University of Oxford · Prof. Andrea Vedaldi · DLA funded
Beginning doctoral research in 3D and geometric deep learning.
2024 to present
ML Research Engineer
Mercedes-AMG Petronas Formula One Team
Applied machine learning research and engineering in a high-performance technical environment.
2023 to 2024
Master's, Computing (AI & Machine Learning)
Imperial College London · Distinction
Deep learning from noisy and imbalanced security data; research later accepted to ACM CCS.