Estimating Tree Damages Using Remote Sensing Data
An investigation using ensemble learning for the classification of tree damage classes to determine forest condition — using the Black Forest as an example.
Senior Data Scientist @ OneData, Berlin
Data Scientist with a background in Business Information Systems and a focus on machine learning, remote sensing, and cloud infrastructure. Currently building data-driven solutions at OneData.
High school diploma graduation
Apprenticeship (IHK Frankfurt) — "Computer Science Expert, Software Development" at Dimension Data Germany
Software Developer & Working Student at Dimension Data / NTT Germany
Full stack development with Angular, Python, and PHP. CI/CD pipelines with Jenkins and SonarQube. Bug analysis and troubleshooting of custom-built solutions.
Associate Partner: Technical Development & Learning and Analytics at NTT Ltd.
Solutions architecture & process automation for HR self-service. BI & data analytics for talent management. ETL-driven license management achieving 40% cost reduction.
M.Sc. Business Information Systems at Frankfurt University of Applied Sciences.
Read about my thesis: Estimating Tree Damages Using Remote Sensing Data.
NTT Client Experience Center — Technical lead for the Client Roadshow at the Tour de France. Responsible for technology, network infrastructure, and connectivity across all event locations.
NTT International Hackathons — Organized and facilitated global hackathon events with partners (Cisco DevNet, Hackathon for Sustainability), bringing together 300+ employees from around the world.
Red Bull Basement — Developed, deployed, and operated a custom private metaverse connecting experts from around the globe to help competitors develop their skills.
Software Engineer at YOUniquehorns GmbH
Developed the KI Stellenmanager — a RAG-based AI system for automated job description evaluation, competency generation, and salary classification for the public sector using vector databases (Qdrant), DSPy, and LiteLLM.
Senior Data Scientist at OneData
Developed Link AI — an entity recognition algorithm that boosts linking accuracy by up to 80%.
Building the foundation for AI agents on the One Data Platform, enabling users to interact with data through intelligent assistants.
Founded and lead the company-wide AI Guild — a cross-team community for sharing AI knowledge, raising questions, and organizing regular meetings.
ML pipelines, automation, data science
RAG, vector DBs, DSPy, agent systems
PostgreSQL, MySQL, MongoDB, Qdrant
AWS, Azure, GCP
Containers, deployment, orchestration
Infrastructure as Code
Python, Java Spring, integration
Jenkins, SonarQube, pipelines
Earth observation, ensemble learning
An investigation using ensemble learning for the classification of tree damage classes to determine forest condition — using the Black Forest as an example.