Freelancer profile translated to English.
Back to original languageAbout Michael
I develop scalable machine learning and geospatial data pipelines for Earth Observation, Agriculture, and Climate. My focus is on combining satellite data, time series, and domain-specific knowledge to build robust models that work in practice – not just in the notebook.
I support companies in developing production-ready services from raw data: from data integration, feature engineering, and modeling to deployment, monitoring, and maintenance. My solutions are used by clients in production and deliver daily added value for risk analysis, agricultural processes, monitoring, and decision support.
Typical results of my work:
- Precise Yield Forecasting Models (EO + WOFOST + ML)
- Automated Pipelines for Sentinel-2, Raster Data & Time Series
- Geospatial Feature Engineering Frameworks
- Climate Risk Analytics & Impact Modelling
- Agent-based Workflows for Scalable Data Processes
I work quickly, in a structured manner, and deliver production-ready solutions that are maintainable in the long term.
Technologies: Python, ML, Time Series, EO/RS, GIS, Raster Data, WOFOST, FastAPI, Docker, Cloud, Vector Embeddings, Agentic Workflows, LLM's
German
Native or bilingual
English
Conversational
Remote only
Primarily works remotely
Experience
- AI IngenieurbüroConsultantDIGITAL AND ITApril 2025 - Today (1 year and 2 months)Munich, GermanyAt the AI engineering office, I develop production-ready ML and geospatial data solutions for clients in agriculture, climate, and environmental sectors. I take technical responsibility for complete end-to-end pipelines – from data acquisition and modeling to integration into existing systems.My role includes:> Building and managing scalable ML pipelines for EO and time series data> Developing time series forecasts and utilizing modern models> Designing agent-based workflows for automating complex data processes> Integrating multimodal data sources (satellite, sensor, historical time series)> Technical consulting on ML architecture, data quality, and model robustness> Close collaboration with clients on transitioning prototypes into production systemsImpact:The models and pipelines I develop are used daily by clients to make data-driven decisions relevant to agriculture and climate, assess risks, and automate processes.
Recommendations
Be the first to recommend Michael
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Dr.-Ing.Technical University of Munich (TUM)2021Dr.-Ing.
- Diploma in Computer ScienceTechnical University of Munich2008Diploma in Computer Science