Senior Machine Learning & Data Engineer

12/2023 – 12/2024

- Developed a predictive recommendation engine for a major entertainment company, utilizing Big Data technologies. This project enhanced user engagement and retention, resulting in an increase in user activity on the platform.
- Developed a geospatial analytics model to calculate and filter rooftop sizes suitable for solar energy cell installations, enabling clients in the renewable energy sector to optimize site selection and enhance sustainable energy initiatives.
- Architected and planned the roadmap for a comprehensive Feature Store, streamlining feature engineering processes and significantly reducing the time required for model training and deployment.
- Designed advanced data pipeline solutions, incorporating scalable and robust data architectures that supported real-time analytics and decision-making capabilities.
- Conducted in-depth technology assessments and provided strategic insights, helping clients to adopt cutting-edge tools and methodologies for improved data-driven decision-making.

Amazon Web Services (AWS), Apache Spark, Big Data, Business Intelligence (BI), Continuous Delivery, Datenmodelierung, DevOps, Maschinelles Lernen, Mysql, Pandas, Python, Software Architecture, SQL

10/2022 – 6/2023

- Led the development of a secure, scalable data storage solution, facilitating efficient model building and R&D efforts.
- Pioneered data augmentation strategies for ML models, enhancing the predictive accuracy for firms with limited data points.
- Authored compliance tests against US regulations for bias and discrimination in predictive hiring models.
- Contributed to the growth of the company's customer base by developing tailored predictive models for small
firms.

Data Science, Entscheidungsbaum Lernen, Kubernetes, Maschinelles Lernen, Pandas, Predictive Analytics, Python, Software Architecture

11/2019 – 9/2022

- Championed the adoption of PySpark, reducing KPI computation time from 24 hours to 18 minutes, and subsequently spearheaded a company-wide workshop on Spark implementation, establishing it as a standard for data-intensive projects.
- Served as the technical lead for the pallet-loading optimization project, orchestrating a solution that resulted in multi-million euro savings by enhancing operational efficiency and reducing truck loading times.
- Automated object detection on video data, transitioning from a 2-month manual labeling process to an automated, minute-scale operation, significantly accelerating the client's data science initiatives.
- Organized and led an internal developer conference, orchestrating 42 presentations with 79 speakers, which cultivated a strong culture of knowledge sharing and innovation across the organization.
- Delivered 6 comprehensive knowledge-sharing sessions on security and vulnerability tools, elevating software quality and establishing new best practices within the engineering team.
- Authored a comprehensive OAuth 2.0 guide for data scientists, which was adopted as a company standard, ensuring secure and standardized authentication practices across all projects.
- Contributed to the development and refactoring of Proof of Concept (PoC) applications, the creation of CI/CD pipelines using Kubernetes, and the enhancement of operability through sophisticated logging, monitoring, and alerting systems.
- Drove analytics optimization by refining model parameters and algorithms, and played a pivotal role in the technical recruitment process, bolstering the team's expertise and efficiency.
- Led the meticulous documentation of application workflows and operational processes, substantially improving
the AI department's knowledge management and procedural clarity.

Data Science, Apache Spark, Postgresql, SQL, Maschinelles Lernen, Objekterkennung, Semantic Segmentation, Qualitätsmanagement / QS / QA (IT), Software Quality, Python, Kubernetes, Kostenoptimierung, Technische Projektleitung / Teamleitung