Lead Data Scientist & Software Engineer

8/2022 – offen

- Introduced new features and refactored critical components in a central Python application

- Refactored >20,000 lines of code, increased test coverage from ~20% to >85%

- Achieved a 5x speed-up in data transfers speeds; crafted coding guidelines for future contributors

Tools: Python, Electron, Docker, Ansible, mypy, pyright, black, ruff, pytest, pylint, Pydantic, Polars, GitHub, Azure DevOps, SAP ABAP / ERP

ETL, Docker, Ansible, Databricks, Git, Microsoft Azure, Projektleitung / Teamleitung (IT), Python, SAP ABAP

4/2022 – offen

The GetML Framework introduces new ML algorithms that boost productivity by 10x in end-to-end prediction modelling on relational & time series data. An open-source edition is available on GitHub.

- Overhauled getML Python API & documentation with updated examples and demo notebooks

- Co-developing benchmark-setting algorithms for automated feature engineering

- Design & set-up of FastAPI + getML blueprint project
Implemented Google Cloud-hosted CI/CD pipeline

Continuous Delivery, Continuous Integration, MLOps, Agile Methodologie, C++, Ansible, Data Science, DevOps (allg.), Docker, Git, Google Cloud, Maschinelles Lernen, Python

9/2019 – 3/2022

Software engineering team lead - managing three developers. Collaborated with product owner & CTO on features, refactoring and reliability engineering

DevOps, Pandas, Tensorflow, Saas, Iaas, Microsoft Azure, Representational State Transfer (REST), Apache Kafka, DevOps (allg.), Git, Kubernetes, Python, SQL