Jannik Castenow

Dr. Jannik Castenow

Machine Learning Engineer at ITSC GmbH

Integrating ML into traditional workflows to make a real difference

About

I'm a Machine Learning Engineer at ITSC GmbH, working in the health insurance sector. I'm passionate about integrating ML models into traditional workflows — supporting and enhancing the work people already do, not replacing it. My goal is to help people live longer, healthier lives by bringing data-driven insights into the processes that matter. I'm particularly interested in RAG-based architectures and scalable ML pipelines.

Education

Ph.D. in Theoretical Computer Science

Paderborn University

My academic background in theoretical computer science gives me a strong foundation for tackling complex, abstract problems and designing rigorous, well-reasoned solutions. This ability to think formally and break down hard problems carries directly into my engineering work — whether it's optimizing ML pipelines, designing scalable architectures, or reasoning about algorithmic trade-offs in production systems.

Tech Stack

ML & Deep Learning

  • PyTorch
  • scikit-learn
  • XGBoost
  • LightGBM
  • CatBoost
  • Optuna
  • Hugging Face Transformers
  • LangChain

Data Engineering

  • PySpark
  • Polars
  • Narwhals
  • Python

MLOps & Infrastructure

  • Kubeflow
  • Kubeflow Pipelines
  • Docker
  • Kubernetes
  • MLflow

Visualization

  • Matplotlib
  • Seaborn
  • Plotly
  • Streamlit

Interests

Production ML

Building robust, scalable pipelines that take models from experimentation to production. Focused on reproducibility, monitoring, and continuous training workflows.

RAG Architectures

Exploring retrieval-augmented generation systems that combine the strengths of large language models with structured knowledge retrieval for more accurate, grounded outputs.