• Entwickeln einer Datenstrategie in Abstimmung mit den Geschäftszielen der Kunden

• Entwerfen und Implementieren von komplexen Datenmodellen und Ontologien

• Schaffen einer konsolidierten Datenbasis

• Sicherstellung der Datenqualität auf höchstem Niveau

• Planen und Gestalten von Datenarchitektur für verschiedene Anwendungen und Systeme

• Entwickeln und Implementieren von Data-Governance-Verfahren

• Auswahl von Datenbanken, Tools und Technologien in Abstimmung mit den Anforderungen unserer Kunden

?     Identification and alignment on generative AI use cases

?     Definition of requirements for each AI use case

?     Assurance of data acquisition and adequacy for AI models

?     Development of generative AI proofs of concept

?     Strategy planning for generative AI deployment

?     Enablement and training of employees on AI systems

?     Conducting of workshops

?     Tools: Azure Open AI, ChatGPT, Gemini, Mistral, Python, Streamlit, RAG

• Stakeholder and business requirement analysis and communication
• Experience working as a data scientist and engineer in the logistics field, with a focus on handling large amounts of data.
• Proficiency in Microsoft SQL, SSIS, and Visual Studio for data extraction, transformation, and loading.
• Expertise in data visualization and reporting using Power BI, including creating interactive dashboards and reports to track key performance indicators (KPIs) and business metrics.
• Strong programming skills in Python, including experience with data manipulation libraries such as Pandas and NumPy, as well as data analysis and machine learning frameworks like Scikit-learn.
• Familiarity with SAP Data Warehouse Cloud (DWC) and SAP Analytics Cloud (SAC), including experience with data modeling, data integration, and creating interactive dashboards and reports.
• Experience working with various data sources, including structured and unstructured data, and using data modeling techniques to create efficient and effective data structures.

• Stakeholder and business requirement analysis and workshops for business understanding 
• Development of a rule-based machine learning method to discover interesting relations between different variables of batteries and production processes 
• Processing of model results for data-driven support of product development and production design under consideration of multiple KPIs (e.g., battery performance and costs) 
• Supporting process experts with valuable insights into data

• Stakeholder and business requirement analysis and workshops for business understanding 
• Data management and big data engineering of ~2500 sensors data per car, including temperatures, humidity, airflow, energy consumption, process parameter and ERP information 
• Building data pipeline to track and trace cars along all processes in the paint shop 
• Model building to identify root causes for main drivers of paint failures 
• Supporting process experts with valuable insights into data

• Stakeholder and business requirement analysis 
• Development of platform architecture for analytics application 
• Development of a data warehouse to acquire and manage data from diverse sources and resolutions in one central cloud storage (based on AWS, ELK-Stack) 
• Development of unsupervised machine learning models to identify different product groups along the value chain to optimize production and factory system (e.g., logistics) 
• Implementation of ML models in AWS 
• Development of a web-based decision support tool for different stakeholders 
• Validation of models and preparation for implementation in serial operation 
• Economic and ecological evaluation of improvement potentials and communication to top management

• Management and preprocessing of data from diverse data sources 
• Definition of requirements for a prediction model 
• Building a deep learning pipeline to predict different risk factors (e.g., damage or breakdowns) on multiple product levels 
• Enabling the integration of human knowledge in the decision-making process 
• Development of interactive dashboards for visualization of results

• Management and preprocessing of data from diverse data sources (e.g., ERP, production data) 
• Building machine learning models to improve multiple KPIs(e.g., truck utilization and throughput times) 
• Combining data analytics with agent-based simulation to optimize transport routing 
• Definition and evaluation of different material supply scenarios 
• Identification and communication of improvement potentials

• Management and preprocessing of energy and production data 
• Statistical analysis and modeling of time series process and energy data 
• Identification of energy consumption improvement potentials to reduce total energy consumption 
• Evaluation of different scenarios and assessment of cost-saving potential 
• Development of user interface and dashboard for visualization of improvement potentials