Scientific machine learning
Designing and validating models for proteomics, remote sensing, 3D data, and high-throughput research workflows.
Research software · AI · Data systems
My breadth spans software, hardware, cloud, IoT, biology, GIS, and climate simulation. That understanding helps me choose the right tools, methods, and orchestration to move quickly from research prototype to production-ready application.

Beyond generated code
Productive engineering comes from understanding the theory, data, hardware, software, cloud, and operations well enough to choose the right abstractions and orchestrate them into one coherent system.
Designing and validating models for proteomics, remote sensing, 3D data, and high-throughput research workflows.
Turning heterogeneous data and experimental code into reproducible systems that researchers can operate and extend.
Aligning scientific goals, architecture, funding, and delivery from prototype through dependable production.
First-author work · ASMS 2021
Evaluated eight classifiers and used genetic algorithms to tune a gradient-boosting model integrated into Spectronaut. Avalon improved peptide-precursor identifications by 20-40% on short-gradient dia-PASEF data while retaining comparable empirical false-discovery-rate performance.
Read the Biognosys abstractMSc thesis · 2020
University of Basel
Artificial Intelligence specialization, focused on short-term temporal patterns in EEG data.
Research record
Journal, conference, and general-assembly contributions connect software engineering with 3D geospatial methods and forest science.
See publications and presentations →