04/2026 – 01/2027
(expected)
Master’s Thesis Researcher
German Aerospace Center (DLR)
- Research at the intersection of chaos theory and machine learning: forecasting nonlinear dynamical and complex systems with reservoir computing.
- Developed a parameter-aware reservoir computing model that forecasts chaotic systems in parameter regimes not seen during training.
Chaos Theory
Nonlinear Dynamics
Reservoir Computing
Time Series Forecasting
Python
06/2025 – present
Working Student, Short-Term Trading
E.ON · Munich
- Develop ML models for wind and solar power forecasting (gradient boosting, neural networks, regularized regression, Optuna) that combine multiple numerical weather prediction sources, benchmarked against operational forecasts Reduced RMSE by 20%.
- Built automated data pipelines on Azure that ingest forecasts and actuals at 15-minute resolution, including backfilling, data quality checks and failure alerting.
- Designed a partitioned Parquet database with automated accuracy metrics, accessible from Databricks and Python.
- Develop and operate dashboards (Plotly Dash, Streamlit) used daily by traders to monitor and compare forecasts; containerized with Docker and deployed via Azure DevOps CI/CD on Kubernetes.
- Resolved production incidents through log-based root-cause analysis, e.g. cutting a dashboard’s memory use by 65 %.
Python
Forecasting
LightGBM
Optuna
Azure
Databricks
Docker
Kubernetes
Plotly Dash
Streamlit
11/2022 – 02/2025
Working Student, Innovation Lab New Materials
Infineon Technologies AG · Regensburg
- Built an ML model classifying materials by their FTIR spectra for reverse engineering.
- Co-designed experimental setups for novel semiconductor materials, analyzed the data and presented results to technical experts.
Machine Learning
FTIR Spectroscopy
Data Analysis
OriginLab
Research