Machine Learning Engineer in Munich

• Taught ML, BI, and Big Data to Master's students.

Tech: Python, Power BI, SQL, ML, SnowflakeDB, databricks, MS Fabric, MongoDB, LLM

• Development of an AI-powered project organization tool for a civil engineering company that intelligently links project, task, tender, schedule, and document data through a knowledge graph.
• Implementation of AI features for document analysis, information extraction, context-based assistance, and voice-based data capture based on Microsoft Azure AI, reducing administrative effort, making information available faster, and supporting project teams in decision-making.
• Tech stack: Python, React, TypeScript, FastAPI, Claude Code, Codex, Graphify, PostgreSQL, Microsoft Azure AI Foundry, Azure OpenAI, Azure AI Speech, Azure AI Document Intelligence, Microsoft Graph, Microsoft Entra ID, Docker, Git, CI/CD.

• Built and operated an end-to-end MLOps platform on Azure ML and Kubernetes (Kubeflow) for automated deployment, monitoring and scaling of forecasting models (e.g. Temporal Fusion Transformer, Informer, Autoformer)
• Implemented CI/CD pipelines in Azure DevOps for the complete ML lifecycle – from resource provisioning (Terraform), data transformation (Hugging Face Datasets, Pandas, PyTorch, CUDA clusters) through training and evaluation to model registry and endpoint deployment
• Integrated MLflow for experiment tracking, model versioning, performance monitoring and automated registration in Azure Model Registry
• Developed and containerized PyTorch training jobs with CUDA (Azure Notebook, Jupyter Notebooks) for price and time series forecasting (PFC models) with automatic rollout via Azure ML endpoints and REST/gRPC interfaces, Docker containerization, secured with OAuth 2.0
• Set up monitoring and alerting mechanisms (Prometheus, MLflow metrics), centralized logging and cost tracking
• Configured security (OAuth2) and rate limiting via APIM
• Automated infrastructure provisioning and model deployment using Terraform, Helm and Azure CLI; integrated with existing market data systems and event pipelines
• Migrated existing workloads and databases (IONOS → Azure, MongoDB) integrating them into central MLOps workflows and internal networks
• Extended the platform with LLM-based tools (LangChain, LangServe) to integrate GPT-based analysis modules into existing Spring Boot services for market anomaly detection and automated reports
• Analyzed and designed a software solution to efficiently process high-volume data (>3000 messages/sec) (market data store)
• Developed Spring Boot / Java 21 containers with RabbitMQ to distribute market data via MongoDB (Kubernetes) with fast data storage in Redis RMaps, deduplication, forwarding of messages to read model queues and building read models for UI display in MongoDB
• Integrated RESTHeart to generate a REST API for MongoDB
• Migrated to MongoDB ClickHouse for mass ingests and automatic deduplication using the ReplicatedMergeTree engine in ClickHouse
• Built a Python Apache Arrow Flight service for querying the ClickHouse DB in milliseconds for complex queries (gRPC protocol / ClickHouse column-based queries)
• Developed an Angular frontend to simplify data queries and master data maintenance
• Used agentic coding with remote and local LLMs (Claude, Ollama Qwen, OpenLLM) and MCP servers
• Created Python scripts for transforming and cleaning incoming market data (Pandas, scikit-learn)

• 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 an advanced, agentic RAG pipeline using LangChain and LangGraph for structured data extraction from PDFs, utilizing tools, state management, and OpenAI LLMs (GPT-4) to improve accuracy and handle complex document structures.
• Developed a Google AI agent for extraction of structured information from PDF documents and deployed the agent on Vertex AI.
• Architected data pipelines using Azure Data Factory and Databricks to ingest data from Azure Blob Storage, process it with PySpark, and load it into Azure SQL Database via Linked Services.
• Containerized AI agents and services using Docker for consistent local development and deployment.
• Utilized PySpark and Dask for database querying in coordination with Azure Blob Storage and Document Storage.
• Created a ReAct agent that extracts structured data from PDF documents using tools and integrating Azure Document Intelligence.
• Contributed to the CPO invoices validation check project using Databricks to find existing CDRs and calculate total valid costs.
• Developed a conversational AI agent (chatbot) with a FastAPI backend, integrating RAG for precise tariff extraction and deployed the service using Azure Container Apps.
• Tools used: Azure, Azure OpenAI, Azure Document Intelligence, Azure Blob Storage, Google ADK, Google Cloud, Vertex AI, Gemini, Databricks, LangChain, LlamaIndex Ollama, Docker, PySpark, Azure SQL, Azure Data Factory, Azure AI Agent, Microsoft SQL Server

• Independently led backend development as the sole contributor and applied computer vision techniques to transform raw SLAM (Simultaneous Localization and Mapping) data into user-friendly CAD models, advancing the product from prototype to release-ready for architectural applications
• Developed and implemented mathematical algorithms to accurately detect room contours and improve the precision of wall-length estimations from spatial maps
• Contributed to reducing human intervention by optimizing backend processes for real-time, automated CAD generation
• Collaborated with cross-functional teams in robotics, data science, and software engineering to enhance system efficiency and scalability
• Stack: Python, C++, OpenCV, NumPy

• It is like a startup within REWE, where we have to build a new forecasting system on Google Cloud Platform from the scratch. Although, officially my role is called MLOps, my actual tasks also include development of data processing pipelines (data engineering) and data scientists tasks such as feature engineering and model trainings.
• GCP: Terraform (tofu), Vertex AI (Kubeflow), Cloud Run, IAM, Google Cloud Storage, BigQuery, Artifact Registry
• Data engineering: Snowflake as the main data warehouse, Terraform, DBT for data model implementations
• CI/CD: GitLab. We have built a CI/CD pipeline that automates deployments of new releases up to production environment
• Development of feature store and data synchronization between environments
• Data science: evaluation of different forecasting models, including CatBoost, Contextual Gamma and Random Forest; implementation of training pipelines using Kubeflow on Vertex AI; scaling and development of an event-driven interface using Kafka as a forecasting service; evaluation of MLFlow for model tracking and model registry
• Implementation of REST API using KeyCloak OAuth2 and OpenID (JWT)
• Monitoring: implementation of dashboards with Grafana, Prometheus, Mimir, Streamlit and Loki to monitor prediction metrics, GCP and Snowflake costs for pipelines, and system metrics
• Development of Copilot Agent Skills

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects