Matplotlib Experts in Munich

• Created a multi-agentic system supported by a knowledge graph to automate drafting of research papers
• Used multiple experts (OpenAI models) collaborating during document drafting
• Extracted useful information from the knowledge graph
• Technologies: LangChain, LangGraph, Smolagents, LlamaIndex, dspy
• Infrastructure: Terraform and GitHub Actions (CI/CD) on AWS
• Deployed initial application as a Streamlit app

AI-driven automation of purchasing on a printing company's website, including selecting delivery times, order options, ordering, payment, and uploading print data from the Lumiz Cloud.

• Migration of existing data jobs from Cognos Data Manager to Tibco/IBI Datamigrator
• Migration data jobs parametrisation for dynamic runs
• Optimisation and cutting-back
• Regression tests
• Knowledge transfer and documentation

• Designed and implemented a full machine learning pipeline for churn prediction using the Telco dataset.
• Applied preprocessing techniques including missing value handling, categorical encoding, feature scaling, and PCA.
• Built and compared over 15 models (logistic regression, random forest, XGBoost, etc.) and evaluated them using accuracy, precision, recall, F1 score, ROC AUC, and PR AUC.
• Tuned hyperparameters with GridSearchCV, achieving 80.6% accuracy with random forest and XGBoost.
• Created visual reports (bar plots, heatmaps, radar charts) to interpret model performance and churn drivers.
• Exported reusable pipelines and trained models with joblib for deployment.

• Designed and implemented a robust Python-based data processing framework that supported the transition from R to Python and significantly improved data science productivity by providing maintainable, standardized modules for frequently used workflows, following coding best practices and DevOps principles
• Evaluated, trained, and deployed machine learning models on cloud platforms and edge devices, enabling fully automated mid-infrared (MIR) data evaluation pipelines that eliminated manual analysis steps and significantly shortened the time from measurement to prediction for customers and internal stakeholders
• Analyzed and interpreted multivariate MIR spectral data from the company’s proprietary analyzer using R and Python, supporting reliable identification and quantitation of chemical compounds in solution

• Led comprehensive AI workshops for professionals, focusing on AI-driven process automation.
• Tech Stack: n8n, Make, LLMs (OpenAI, Anthropic), Prompt Engineering, Process Mapping Tools.

• Lead Architect to design and implement the data lake and ETL Pipeline using AWS Stack
• Performance Optimization of Data Ingestion of ETL Pipeline
• Development of Data Validation using Great Expectations
• Leading of the data migration for two sources exchanges
• Data Modeling in AWS Redshift

MLOps

• Model inference implementation by mlflow and AWS SageMaker
• Feature Engineering for the running ML Models ( Recommender Engineer, Clustering )
• Implementatino of Model Registry and artifactory using mlflow
• Historization an Profiling of the Input Data Using AWS Glue Crawler and AWS Data Catalog
• Feature importance using mlflow

Tech. Stack: Python 3, AWS Glue, AWS Step Fucntion, AWS Lambda, AWS EventBridge, AWS IAM Role, AWS SageMaker, AWS EC2, AWS Glue Crawler, AWS CloudWatch, MLFlow, ETL, Data lake, GitHub Action, Terraform, Jenkins, Ansible playbooks (Infrastructure as Code), CI/CD, GitLab, SQL, PySparkSCRUM, Agile, Jira, BigData, VSCode, DBeaver, MSSQL, MySQL, grafana, Docker, Linux, Bash, MapReduce, Data Modeling (ORM), Pandas, YAML, SQL-Alchemy

• Introduced an integrated approach for structural damage detection across concrete, steel, and glass using advanced technologies such as LiDAR and thermal imaging. Highlighted cross-material interactions to enhance diagnostics and enable predictive maintenance.

• Developed an NLP-based medical note simplifier that transforms complex clinical instructions into plain, child-level English. Applied prompt engineering with Flan-T5 transformer models to extract patient-relevant actions and rephrase them into clear to-do items. Built dual Flask and Tornado backends with a printable web interface.

• Research and develop models for chatbots, NLP and LLMs (e.g. Llama, Qwen, OpenAI)
• Enhance chatbots with RAG, in-context learning
• Supervised fine-tuning (PEFT, LoRA), Huggingface or Unsloth
• Advanced training methods: Test-time training, (transductive) active learning, reinforcement learning
• High-throughput serving with vLLM
• Apply embedding models (e.g. SentenceTransformers), similarity/vector search or vector DB or ranking (e.g. LlamaIndex, Faiss, LangChain)
• Generate and filter synthetic data, clustering
• Detect hallucinations
• Evaluate chatbot models (Rouge, BLEU, F1-Score, Recall, Precision)
• Visualization of experiments (matplotlib)

• Developed web scraping scripts to extract and parse over 5000 product data from the Zalando website.
• Performed ETL processes using Apache Spark in CDSW, loaded the data into the Hadoop ecosystem (HDFS), and managed data using Hive and Impala.
• Implemented machine learning algorithms, achieving 85–90% accuracy on multi-class product classification.
• Integrated Zalando's product and price data into the dashboard with Otto and Takko for interactive visuals.

• Generated synthetic datasets for CXR, mammography, and distal radius fracture detection using GANs and diffusion, creating >50k synthetic images for benchmarking.
• Ensured GDPR-compliant workflows and reproducibility, enabling dataset adoption for internal validation and academic collaboration.
• Project highlighted in MedTank’s internal R&D showcase as a flagship synthetic data initiative.

• Building the company with a focus on connectivity for IIoT and Industry 4.0, iRPA/process automation, advanced robotics and smart systems, sensors and services
• Project management and software architecture for IoT gateway development (since 2020) with protocol translation, IT/OT convergence and GRC
• Developing RPA bots for automating and monitoring industrial processes with an agent-based AI approach (since 2020)
• Implementing unsupervised clustering and anomaly detection for time series data in big data streaming pipelines (since 2021)
• Introducing a Docker-based release train for OTA updates with DevSecOps and CI/CD (since 2018)

• Developed a Streamlit ML application utilizing a RandomForest model (Scikit-learn) for predicting smoking behavior, employing Pandas, NumPy, and Matplotlib for data analysis and visualization; deployed on AWS using Terraform for EC2, IAM roles, and S3 buckets, with Pickle for model storage.

• Mastered AWS services including S3, EC2, CloudFormation, IAM, and Auto Scaling, focusing on advanced features like versioning, CORS, ETags, and checksums through AWS-Examples-Freecodecamp.

• Developed and optimized CI/CD pipelines with GitHub Actions to deploy static websites on GitHub Pages, enhancing automated validation, deployment, and maintenance processes.

• Created and deployed a classic Snake game using Flask, containerized with Docker and deployed on Render.

• Improved error rate in Speed Limit elements from 24% to 8% by implementing an LLM pipeline on detected objects (with natural lower bound of 6% as image coverage is only 94%).
• Extensive ML modeling of Routing Cost Function (objective function, features, hyperparameters, training data generation) which led to setting the foundation for a rebuild of a more flexible setup.
• Initiated the first Prioritization Framework for Data Curation Ops ($2M annual organizational expenses) which moves away from daily quotas and now optimizes for ‘expected business value per time unit’, achieving around 5-7% efficiency improvement.
• Close collaboration with Software Engineering & Data Engineering as well as Product & Operations.