Peter Kienle Email & Phone Number

81241 München

Kaufering, Bayern, Deutschland

- Data scientist on the publicly funded research project LIFEDATA, together with University of Augsburg and Deutsches Herzzentrum München- detailed project description: https://www.gesundheitsforschung-bmbf.de/de/lifedata-framework-und-algorithmen-zur-kosteneffizienten-entwicklung-von-deep-learning-10887.php- research on active deep learning to reduce the amount of needed annotated data by usage of special model-based selection strategies- Implementation, training and optimization of deep learning architectures for classification of dermatoscopic images and electrocardiogram (ECG) signals- automation of the entire ML cycle for experimental and productive pipelines using a variety of MLOps tools (GitLab CI, Docker, dvc, MLFlow)

München

- Design of advanced analytics models to give clients insights for making business-relateddecisions- Successful completion of client data science projects for predictive analytics- Development of Python and SQL scripts for ETL processes- Generation of custom data reports which are outside the scope of standard reporting tool solutions- Guiding key client projects to success by solving their data-related issues

München

- Go-to person for data questions related to metrics calculations and historical trend scores of the IBM Enterprise Survey Engagement product- Automation of complex data integrity checks (SQL, Python, SPSS) while working with data from different source systems- Strengthening the customer relationship by the innovative implementation of special configurations for data reporting solutions- Pivotal contact point for questions regarding data analysis and data management

München

- Data governance for multiple simultaneous survey client engagements, including the provision of technical support and assurance of data quality- Consultation on general data best practices- Preparation, cleaning and consolidation of data files containing employee demographic and organizational data before import into existing database schemas- Integration and mapping of third-party source files- Documentation of internal processes for data processing and calculation of key metrics