freiberufler Data Scientist and Architect auf freelance.de

Data Scientist and Architect

zuletzt online vor 8 Tagen
  • auf Anfrage
  • Chemnitz
  • auf Anfrage
  • de  |  en
  • 19.09.2026
  • Contract ready

Kurzvorstellung

Freelance data scientist and software developer with strong expertise in predictive modeling, automation and scalable data systems.

Auszug Referenzen (1)

"Sehr angenehme Zusammenarbeit. C. hat unsere Anforderungen an das Projekt gut verstanden & stand uns mit Ratschlägen zur Umsetzung zur Seite"
Excel & PowerQuery Developer
Joanna Wilbert
Tätigkeitszeitraum

6/2023 – 6/2024

Tätigkeitsbeschreibung

Automation and optimization of MS PowerQuery-based workflows to structure and prepare multi-channel marketing campaigns (Google, Instagram, Youtube, etc.).

Eingesetzte Qualifikationen

Power Bi, Google Cloud, Microsoft Excel

Geschäftsdaten

 Freiberuflich
 Steuernummer bekannt
 Berufshaftpflichtversicherung aktiv

Qualifikationen

  • Amazon Web Services (AWS)2 J.
  • API-Entwickler2 J.
  • Berater Umwelt, Gesundheit und Sicherheit
  • Data Science
  • Datenanalyse
  • Datenbank-Analytiker2 J.
  • Datenbankentwicklung1 J.
  • Datenmodelierung2 J.
  • Docker3 J.
  • Langchain2 J.
  • Large Language Models
  • Machine Learning
  • Neuronale Netze1 J.
  • Postgresql
  • Python4 J.
  • R (Programmiersprache)4 J.
  • SQL3 J.
  • Web Entwicklung2 J.

Projekt‐ & Berufserfahrung

Automation Consultant
Gebr. Donner GmbH & Co. KG, Claußnitz
4/2026 – 5/2026 (2 Monate)
Bauwirtschaft, Anlagen- und Schiffbau
Tätigkeitszeitraum

4/2026 – 5/2026

Tätigkeitsbeschreibung

The project addressed a practical integration gap in an existing timber processing workflow: part labels were required for reliable identification on site, but the processing machine's original printer setup could no longer be used and compatible replacements were unavailable. I implemented a lightweight Windows automation service that monitors the processing machine's output files, parses the relevant metadata, and maps the extracted values to ZPL output for a generic Zebra label printer. The solution was packaged as a standalone executable and configured for unattended startup via Windows Task Scheduler.

Eingesetzte Qualifikationen

Python, Windows Powershell

Data Quality Consultant
Landesbetrieb Forst Brandenburg, Eberswalde
12/2025 – offen (10 Monate)
Öffentliche Verwaltung
Tätigkeitszeitraum

12/2025 – offen

Tätigkeitsbeschreibung

In a federal forest monitoring program, I support data quality and operational workflows for meteorological and soil sensor data from distributed field plots. The work currently focuses on three areas: automated quality control and anomaly detection scripts, a Shiny-based review application for segment-level data correction, and a field-oriented data model for mobile monitoring with QGIS/QField. The goal is to make quality assessment more systematic, reduce manual rework, and establish a stable data foundation from field collection to reporting.

Eingesetzte Qualifikationen

Berater Umwelt, Gesundheit und Sicherheit, Datenanalyse, Datenmodelierung, Postgresql, R (Programmiersprache), SQL

Biodiversity Data Scientist
Centre for Integrative Biodiversity Research, iDiv, Leipzig
6/2024 – 9/2025 (1 Jahr, 4 Monate)
Hochschulen und Forschungseinrichtungen
Tätigkeitszeitraum

6/2024 – 9/2025

Tätigkeitsbeschreibung

I built a scalable biodiversity analytics stack at iDiv, with a primary focus on operationalizing the symobio R package as the data-engineering backbone. Using DuckDB, Arrow/Parquet, and modular targets workflows, the platform standardized heterogeneous occurrence and environmental data into reproducible, analysis-ready outputs while enabling local processing of tens of millions of records. On top of this foundation, I implemented and compared species distribution modeling workflows, including multi-species deep learning approaches.

Eingesetzte Qualifikationen

Predictive Analytics, Datenbankentwicklung, Datenmodelierung, Neuronale Netze, Python, R (Programmiersprache), SQL

Full Stack Developer & Data Scientist
KWS Saat SE & Co. KGaA, Einbeck
5/2024 – offen (2 Jahre, 5 Monate)
Life Sciences
Tätigkeitszeitraum

5/2024 – offen

Tätigkeitsbeschreibung

At KWS Saat, I have been building and extending a Python-based discovery platform for plant breeding research. The work spans backend API engineering, interactive analytics application development, and AI-assisted research workflows, with responsibilities ranging from schema design and validation to CI/CD and deployment hardening. The resulting platform helps researchers explore complex biological relationships and access advanced analysis tools through a practical, user-facing interface.

Eingesetzte Qualifikationen

Langchain, Amazon Web Services (AWS), API-Entwickler, Datenbank-Analytiker, Docker, Python, Web Entwicklung

Excel & PowerQuery Developer
Offerista, Berlin
6/2023 – 6/2024 (1 Jahr, 1 Monat)
Medienbranche
Tätigkeitszeitraum

6/2023 – 6/2024

Tätigkeitsbeschreibung

Automation and optimization of MS PowerQuery-based workflows to structure and prepare multi-channel marketing campaigns (Google, Instagram, Youtube, etc.).

Eingesetzte Qualifikationen

Power Bi, Google Cloud, Microsoft Excel

Senior R Developer
European Central Bank (ECB), Frankfurt
8/2022 – 2/2024 (1 Jahr, 7 Monate)
Banken
Tätigkeitszeitraum

8/2022 – 2/2024

Tätigkeitsbeschreibung

I contributed to modernizing the reporting stack behind key ECB economic publications, with a primary focus on building and maintaining an R package ecosystem for dynamic report generation. The packages enabled consistent, parameterized production of publication-ready outputs across formats and teams, forming the technical backbone of official ECB reporting workflows. Shiny components and enterprise integrations complemented this package core by linking report production to source systems and workflow orchestration.

Eingesetzte Qualifikationen

Agile Methodologie, Dokumentenmanagement, Git, Jira, Python, R (Programmiersprache), SQL

Softwarentwickler (Festanstellung)
Karlsruhe Institut für Technologie, Karlsruhe
11/2021 – 6/2022 (8 Monate)
Hochschulen und Forschungseinrichtungen
Tätigkeitszeitraum

11/2021 – 6/2022

Tätigkeitsbeschreibung

I developed a web application for vegetation data standardization and exchange at KIT. The app was built as a golem-based Shiny package and combined a guided user interface with XML validation, schema-aware conversion logic, and interactive file handling. The app enabled researchers to standardize, validate, and exchange vegetation data in accordance with the Veg-X XML standard, facilitating collaboration across research teams.

Eingesetzte Qualifikationen

Docker, R (Programmiersprache), Server Administration, Web Entwicklung, XML

Ausbildung

Biodiversity, Ecology & Evolution
Dr. rer. nat.
Georg-August University of Göttingen
2019
Göttingen
Biodiversity, Ecology & Evolution
M. Sc.
Georg-August University of Göttingen
2014
Göttingen
Umweltmonitoring / Umweltanalyse
B. Sc.
HTW Dresden
2012
Dresden

Über mich

Freelance data scientist and software developer specialising in predictive modelling, automation, and scalable data systems. I help organisations turn complex data into reliable, production-ready solutions – from data platforms and REST APIs to interactive web applications and AI-powered tools. Proven track record in regulated and research driven environments (finance, biotech, public institutions), with a strong focus on robustness, maintainability, and clear communication.

Professional Skills

Analytical thinking
Independent problem solving
Creativity
Effective communication
Scientific expertise (biodiversity & climate)

Programming

Python, R, SQL, JavaScript, M (Power Query language)
HTML, CSS, XML
Package development (Python & R)
API design (FastAPI, Flask)
ETL / ELT pipelines
Geospatial processing (GIS, terra, sf, raster)
Scripting & workflow automation

Machine Learning

Classification & regression: linear models, tree-based methods, neural networks
Hyperparameter tuning, cross-validation, model evaluation
Bayesian modeling
Dimensionality reduction, Clustering
Technologies: XGBoost, scikit-learn, caret, PyTorch, NumPy, dplyr, pandas, JAGS, Stan

Databases

Data modelling, schema design, data normalization
Query design and optimization
OLTP & OLAP systems
Technologies: MySQL, PostgreSQL, DuckDB, OracleDB, Neo4j

Visualization & Reporting

Interactive reports
Dashboards, Graph Visualization
Automated documentation
Technologies: R Shiny, Plotly Dash, quarto, markdown, plotly, ggplot

Development & Orchestration

Version control: Git, GitHub, GitLab
Cloud: AWS, GCP
Containers & environments: Docker, pip, conda, venv, renv
IDEs & notebooks: VS Code, RStudio, Jupyter, Positron
Workflow automation: make, targets, Camunda
OS & scripting: Linux, Bash, Windows
Agile tools: Jira, Confluence, Slack, Teams

Persönliche Daten

Sprache
  • Deutsch (Muttersprache)
  • Englisch (Fließend)
Reisebereitschaft
auf Anfrage
Arbeitserlaubnis
  • Europäische Union
Home-Office
bevorzugt
Profilaufrufe
386
Berufserfahrung
7 Jahre und 6 Monate (seit 03/2019)
Projektleitung
3 Jahre

Kontaktdaten

Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.

Jetzt Mitglied werden