Christian König

Freelance Data Scientist & Software Engineer.

$ ./get_profile_info.sh
▸ Name: Christian König
▸ Focus: Full-stack Data Science & Engineering
▸ Location: Chemnitz, Germany (Remote & On-site)
▸ Project Experience: Biotech, Finance, Marketing, Scientific Research, Forestry
▸ Title: Dr. rer. nat.
▸ Background: Biodiversity science

Expertise

Philosophy

Scientific Rigor

I bring the methodology of leading scientific research to industrial data. I deliver models that don't just "score well" but are validated, reproducible and plausible.

Clean Engineering

Sustainable software is built on solid engineering principles. I prioritize modern technology, professional design patterns and production-ready packaging in both Python and R.

Decision Intelligence

Data is only valuable if it leads to action. I build the interactive bridges – Dashboards, APIs, and Tools – that translate complex raw output into clear, actionable business logic.

Skills

$ ./list_skills.sh
Programming Languages:
[Python] [SQL] [R] [JavaScript] [Shell scripting]
Machine Learning & AI:
[Regression] [Classification] [Hyperparameter tuning] [Model Evaluation] [Agentic workflows] [Anomaly Detection] [XGBoost] [PyTorch] [scikit-learn] [caret]
Web & APIs:
[HTML] [CSS] [async/await] [FastAPI] [Flask] [Plotly Dash] [R Shiny]
Data Engineering:
[PostgreSQL] [MySQL] [DuckDB] [Neo4j] [pandas] [tidyverse] [PowerQuery] [Apache Airflow]
Visualization & Reporting:
[Plotly] [R Markdown] [Quarto] [ggplot2] [matplotlib]
Tooling & Infrastructure:
[Linux] [Git] [Docker] [AWS] [On-premises hosting] [CI/CD] [Camunda] [Jira]

Education & Background

2008 – 2012
B.Sc.
HTW Dresden
Environmental Monitoring
2012 – 2014
M.Sc.
University of Göttingen
Biodiversity, Ecology & Evolution
2015 – 2019
Dr. rer. nat.
University of Göttingen
Biodiversity, Ecology & Evolution
2019 – 2021
Postdoctoral Researcher
HU Berlin • University of Potsdam
Research and teaching
2021 – Present
Freelance Developer
König Data Solutions
Data Science and Software Engineering

Services

Machine Learning

  • Development of predictive models and classification systems
  • Design and implementation of spatial and time-series models
  • Model evaluation, validation, and monitoring

Generative AI

  • RAG-powered AI assistants and NLP integration
  • Vector databases and semantic search
  • Agentic workflows and automated tool integration

Data Engineering

  • Architecture design for transactional (OLTP) and analytical (OLAP) systems
  • Graph-based modeling and knowledge graphs
  • Performance-focused ELT/ETL pipeline development

Reporting & Analytics

  • Production-ready interactive web applications
  • User-centric internal tools for data exploration
  • Reproducible, automated reporting and document generation

Infrastructure

  • Setup of containerized environments with Docker and Docker Compose
  • Automated CI/CD pipelines for seamless app delivery
  • Linux server configuration and secure on-prem setups

Research Support

  • Implementation of standards for computational performance and reproducibility
  • Internal R and Python package development
  • Hardening scientific prototypes for production environments

Portfolio

Dec 2025 – Present

Environmental Monitoring Platform | LFB

Data quality assurance • Infrastructure

Optimization of data pipelines to improve data quality and availability. Implementation of algorithms for anomaly detection. Data storage and provisioning with PostgreSQL and Supabase.

PostgreSQL • Python • R • Supabase • Anomaly Detection • Data Ingestion
May 2024 – Present

Data Intelligence Platform | KWS Saat

Biotechnology • Full-Stack Development

Development of a data analysis and visualization platform for plant breeding using FastAPI, Neo4j, and Plotly Dash. Interactive network visualizations with Cytoscape. Integrated generative AI models to support data-driven breeding decisions.

Python • FastAPI • Neo4j • Plotly Dash • Cytoscape • LangChain • AWS • Docker
Jun 2024 – Sep 2025

Technical Infrastructure for Biodiversity research | iDiv

Research • Data Science

Built an integrated data platform for heterogeneous ecological data types. Designed a DuckDB-based storage architecture for efficient spatial operations and developed automated R-package pipelines for data ingestion. Implemented advanced multi-species modeling using Deep Learning and ensemble predictions.

R • DuckDB • torch • caret • Ensemble Modeling • targets • Spatial Data
Jun 2023 – Oct 2024

Process automation | Offerista Group

Digital Marketing • Data Automation

Optimized and automated localized digital marketing workflows. Restructured complex MS Excel/PowerQuery data architectures to improve maintainability and performance. Implemented automated data validation and cleaning, with direct integration of external resources via Looker API.

MS Excel • PowerQuery • Looker API • VBA
Aug 2022 – Feb 2024

Reporting Infrastructure | European Central Bank

Finance • Enterprise Systems

Migrated the technical infrastructure underlying the ECB's financial reporting system. Developed a custom R-package ecosystem and a collaborative R-Shiny interface for automated report generation. Integrated with Oracle DB, Camunda workflows, and enterprise document management systems in an agile Scrum environment.

R • R Shiny • Python • Camunda • OracleDB • GitLab API • Timeseries Data
Nov 2021 – Jul 2022

Interactive Data Standardization Tool | KIT

Research • Web Application

Developed an R-Shiny web application for researchers to standardize and share vegetation data. Implemented robust XML processing pipelines for data validation and schema compliance. Optimized system performance and managed deployment through Dockerized server environments.

R • R Shiny • XML • Docker • Scientific Data

Get In Touch

Ready to turn your data challenges into competitive advantages? Let's discuss!