05.09.2026 aktualisiert
100 % verfügbar
Data Science / Data Engineering / Python Development
Wittlich, Deutschland
Deutschland
PhD in Electrical Engineering and Information Technology (Dr.-Ing.)Skills
Data AnalysisPythonMachine LearningData SciencepandasScikit-learnDatabricks
Languages & core: Python (Pandas, Polars, Numpy, Pydantic, FastAPI), SQL, Bash
Data & cloud: Snowflake, db, Postgres, Spark / Databricks, AWS (S3, Batch, Lambda, Step Functions, EventBridge Scheduler, CloudFormation), Azure (AzureML, DevOps Pipelines, Application Insights), Docker, Kubernetes, Datadog
Machine learning: Scikit-learn, XGBoost, Prophet, BoTorch, Scikit-Optimize, MLflow — statistical modelling, time-series forecasting, black-box optimization, model calibration & evaluation
AI-assisted development: GitHub Copilot, Anthropic (Claude) and OpenAI models — code migration, refactoring, test generation and day-to-day development
Engineering practice: Unit & integration testing (Pytest), CI / CD, Git, MLOps, monitoring & alerting, code review, refactoring and stabilization of large code bases
Ways of working: Agile team lead (SCRUM), requirement & stakeholder management, project management, mentoring, presenting to executive and non-technical audiences
For more information, please have a look at the full CV including a project list.
Erfahrung
Berufserfahrung5 - 10 Jahre
Freelancer seit2022
Sprachen
DeutschMutterspracheEnglischverhandlungssicher
Projekthistorie
The Power and Commodity Market Report was developed as a tool for analysts and traders to analyze forecasts from various providers and current market data to facilitate trading activities and investment decisions. It superseded, automated and extended two previous manually updated reports and was re-designed from scratch.
Tasks:
- Design and implementation of the report backend based on Python, Snowflake and AWS
- Ingestion of long and medium-term forecasts and power market data from various internal and external sources from files, APIs and databases
- Harmonization, processing, aggregation and mapping of data from various providers to achieve comparability between their forecasts and market data (including currency conversion, inflation adjustments, mapping of technical terms and geographic definitions)
- Definition and Implementation of the data model for Snowflake using dbt
- Automation of the data ingestion and data harmonization jobs
- Close collaboration with subject-matter experts (analysts) and front-end developers
Large-scale migration project for the ECB. Development of a new data platform and migration of all data & business processes (time-series) from the legacy system to the new platform. Project consists of several agile development teams working together on a large python code base (>100.000 lines of code).
Tasks:
- Team lead (before: Senior Developer) of an agile team of 10 developers practicing SCRUM
- Definition, implementation and maintenance of a calculation & validation engine for time-series data including data processing & aggregation, statistical estimations and forecasting
- Development and maintenance of a common function library
- Migration of data & business processes from the legacy system to the new platform
- Development of unit tests for all components (engine, library & data / business processes)
In-house Data Science consulting covering a broad range of use-cases across the organization:
- Lead and contributed to several Data Science / machine learning POCs and projects with different business contexts: customer credit risk assessment, smart debt collection, product quality optimization, chemical experiment design and formulation optimization, energy demand forecasting, hair health assessment from sensor measurements, etc.
- Mentored junior data scientists in multiple projects on problems concerning machine learning techniques, infrastructure, deployment, and scaling.
- Consulted data science use-cases in the ideation phase and conducted quality assurance on projects with external implementation partners in all phases of the project lifecycle
- Lead an initiative to standardize the team internal data science toolchain. This included requirement analysis, evaluation of platform options (AzureML and Databricks), deploying and configuring an experimental AzureML environment, creating a demo application and conducting training sessions for the team. Contributed to automation of AzureML workspace deployment.
- Advocated the application of principles from software engineering and DevOps in machine learning projects. Pioneered Spark (Databricks) CI / CD workflows including unit and integration testing in close collaboration with Henkel's DevOps team.
- Contributed to the digital upskilling within the Finance department with two separate presentations about machine learning use-cases in Finance that were broadcasted to hundreds of Henkel's employees.
- Created a data challenge that was used as part of the recruitment process for the team and regularly assisted and conducted technical interviews.
- Technologies: Python, Pandas, Numpy, Scikit-learn, XGBoost, Spark, Databricks, Prophet, MLflow, Azure ML, Matplotlib, Seaborn, Plotly dash, BoTorch, Scikit-Optimize, MS SQL, Docker, Kubernetes, Brigade, Azure, Azure DevOps Pipelines, Git, Linux, MacOS