I am a Senior Machine Learning Engineer and Computational Materials Scientist with over 10 years of R&D experience across Microsoft Quantum, University of Zurich, EPFL, and UCL. I specialize in developing scalable AI solutions and integrating advanced Deep Learning models directly into physics-based workflows.

My focus lies at the intersection of accelerated data science, high-performance computing (HPC), and complex data analysis. I recently passed the NVIDIA Certification in Accelerated Data Science.

• Accelerated Data Science & ML Engineeering: PyTorch (Python & C++ API), Graph Neural Networks, Active Learning, RAPIDS Library (CuDF, CuML, CuPy).
• HPC & Cloud Infrastructure: Azure Quantum Elements, Azure HPC, Multi-node GPU/CPU Scaling, CUDA, MPI, Slurm.
• Software Engineering: Python, C/C++, Fortran, Bash, Azure DevOps, CI/CD.

• Deep Learning Integration in CP2K: Developer responsible for bridging classical physics frameworks with data-driven AI. Designed the interface between PyTorch C++ and Fortran 2008 to embed Equivariant ML Interatomic Potentials directly into the CP2K quantum chemistry suite (See PR #4898).
• Accelerated Materials Discovery: As a Senior ML Engineer at Microsoft, I developed high-throughput ML workflows and optimized large Azure Cloud HPC for the Azure Quantum Elements platform to accelerate simulations for materials discovery.

As a Principal Investigator (PI) for the Swiss National Science Foundation (Ambizione) and PRACE EU, I have led a large-scale computational research project:

• Funding of Computational Resources: Secured funding and a 3-year-long allocation for tens of Millions of CPU-hours of on tier-0 Swiss National Supercomputers.
• Scientific Lead: Directed research strategies and led scientists in applying Deep Learning and Density Functional Theory to solve complex nanofluidic and energy conversion problems.

	The role of the water contact layer on hydration and transport at solid/liquid interfaces PNAS (2024) Applied active learning frameworks to uncover new water purification phenomena.
	SimPoly: Simulation of Polymers with Machine Learning Force Fields Derived from First Principles arXiv pre-print (2025) Collaboration with Microsoft Research on ML interatomic potentials.
	Friction of Water on Graphene and Hexagonal Boron Nitride from Ab Initio Methods Nano Letters (2014) Discovered friction mechanisms of water on 2D materials.