Project Portfolio

  • Python Developer, Frontend and Backend
    2023 University Cologne (CECAD Imaging Facility)

    Development of an exporter for OMERO, a database for biomedical image data

    Tasks:
    • Extension of the open source command line tool omero-cli-transfer to transfer research data from the OMERO database to ARC repositories.
    • Development of a mapping specification for transferring OMERO projects to ARC repositories.
    • Extension of the OMERO web frontend to display ARC metadata and control data export.
    • Documentation

    Tools:
    PythonOMEROPostgresDjangoGitGithub ActionsDockerPytest

  • Python developer, ML Engineer, AI Expert (image analysis, computer vision)
    2023

    Automated detection of neurons in microscopic images with artificial intelligence.

    Tasks:
    • Development of a command line tool for Deep Learning based recognition of cell objects in large image files (>10GB)
    • Development of a workflow for users to train an individual Deep Learning model and for quality control purposes
    • Consulting for optimization of data measurement (confocal microscopy).
    • Documentation

    Tools:
    PythonTensorflowScikit-Imageaicsimageiocellpose

  • Data Scientist
    2023 Industry

    Feature ranking analysis for an industrial manufacturing facility.

    Tasks:
    • Data import
    • Data cleansing
    • Explorative data analysis
    • Feature analysis
    • Training of supervised machine learning models
    • Feature ranking analysis with SHAP
    • Documentation

    Tools:
    PythonPandasScikit-LearnMachine Learning

  • Python Developer / Data Engineer
    2023 DekaBank

    Frontend and backend development of a web application for portfolio management.

    Tasks:
    • Frontend and Backend development with Python and Javascript
    • Design of the class-based software architecture in the backend
    • Data model design (combination of relational and json based model), implementation of test, staging and production database
    • Documentation
    • Setup of continuous integration pipeline (package installation, unit testing, pep8 checks, automated builds of documentation)
    • Work within an interdisciplinary team of financial experts, software developers and analysts

    Tools:
    PythonPlotly DashPydanticMypySphinxGitlabPandasMssqlPytestJavascript

  • Python Developer / Data Engineer
    2022 DekaBank

    Frontend and backend development of a business intelligence web application.

    Tasks:
    • Frontend and Backend development
    • Development of data buffering solutions for fast data provision of fragmented data sources.
    • Handling and effective provisioning of big data tables.
    • Implementation of a business intelligence web app
    • Refactoring prototype scripts to production code (unit tests, continuous integration…)
    • Work within an interdisciplinary team of financial experts, software developers and analysts

    Tools:
    PythonPydanticMypyPlotly DashFlaskGitlabPandasMssqlPytestMLflowParquetJavascript

  • Data Scientist and Data Engineer
    2021 Medium-sized Trading and Logistics Company

    Development of AI based sales prediction models.

    Design and implementation of an AI-supported prediction model for sales of print media in magazine distribution, prototyping, implementation and deployment of the productive system.

    Tasks:
    • Conception of a deep learning model for the prediction of sales figures
    • Development of a data model and ETL processes for processing raw data
    • Implementation of the automated prediction service based on an AI model

    Tools:
    TensorflowPostgresMS SQL ServerPythonSqlalchemyAlembicDockerdocker-composegit

  • Data Engineer / Project Lead
    2020 Research Institute

    Design and implementation of a Postgres database for data management of an automation system.

    An automation plant produces sensor data of various types, which are fed into mathematical prediction models together with various metadata. Measurement data and metadata are to be stored centrally in an SQL database. The project requires close interaction with employees who operate the automation system and evaluate the data. The interdisciplinary team includes biologists, chemists, technicians, data analysts and software developers.

    Tasks:
    • Project management
    • Development of the data model in numerous workshops.
    • Development of import specifications in close cooperation with future users.
    • Implementation of the model in Python/Sqlalchemy
    • Setting up a Postgres test database with docker-compose and Gitlab-CI
    • Implementation of importer tools in Python.

    Tools:
    PostgresPythonSqlalchemyDockerdocker-composeGitlab-CI

  • Data Scientist / Python Developer
    2019

    Development of a machine learning application for the analysis of sensor data.

    Highly noisy time series data are recorded via a sensor within a measuring apparatus. In these time series, sporadically occurring events are to be automatically detected and characterized. For this purpose, a machine learning software with MVC architecture was implemented in Python. The software includes the following functionality: Filter and normalize the raw data, calculate robust metrics based on the pre-processed data, provide a graphical user interface to display data and interactively create training data sets, automatic detection of events using a supervised machine learning method, export of the result data.

    Tools:
    PythonTkinterScikit-Learngit

  • Python Developer / Project Lead
    2016

    Development of YAPiC, an open source software for analyzing biomedical image data using deep learning.

    Tasks:
    • Project management
    • Conception and algorithm development
    • Presentation of the software at international conferences
    • Deployment, development of CI/CD pipelines
    • Management of the further development of the tool by the open source community

    Tools:
    PythonTensorFlowTravis-CIGitHub

    YAPiC Website
  • Data Scientist / Image Processing Specialist
    2017

    Automated characterization of tissue samples using deep learning

    As part of a medical research project, tissue samples were photographed with an automated microscope. Based on Python and Tensorflow, software was developed to identify and classify specific cell types in the tissue. In this way, different cell types could be counted automatically for user-defined tissue regions.

    Tools:
    PythonTensorFlowgit

  • Python Developer, DevOps
    2018

    Development of a parallelized image analysis pipeline for processing massive image data of an automated microscope.

    An automation system within a pharmaceutical laboratory produces terabytes of image data daily. Based on CellProfiler software, object recognition and feature calculation was implemented to extract structured data from the raw image data. For robust deployment on an in-house CPU cluster, the application was containerized with Docker and orchestrated with SLURM.

    Tasks:
    • Definition of the specifications in collaboration with the domain experts
    • Planning and acquisition of necessary hardware
    • Conception and implementation
    • Big Data handling

    Tools:
    PythonCellProfilerDockerSLURM

  • Data Scientist Drug Discovery
    2014

    Drug Screening Analysis including Feature Engineering, Clustering and Ranking Analysis

    Tasks:
    • Setup and execution of image analysis pipeline for automated object detection of image based drug screening data.
    • Feature processing and selection
    • Clustering analyses to identify drug candidate groups
    • Development of ranking algorithms to identify drugs with high potential and low toxicity
    • Big Data processing

    Tools:
    PythonCellProfilerPandasNumpyScipyScikitLearnApache Spark