Git Experts

I designed and built a self-service AWS platform for Data Science teams with little or no infrastructure-as-code experience. A team writes about 10 lines of Python and gets a deployable stack with full SDLC release cycle that already follows the governance rules. Networking, encryption, IAM and tagging are decided by the platform, not by each team.

New teams or AWS accounts are onboarded with one pull request. Waste prevention and cost control is built into the defaults: Data scientists don't need infrastructure skills.

• Construct library (AWS CDK, Python). Built a versioned catalog of about 20 hardened constructs for being used in data-science projects with ML context
• Governance as code
• Multi-account, multi-tenant
• Golden-path scaffolding
• CI/CD and supply chain. Built reusable GitHub Actions workflows
• Release engineering
• QA with e2e, contract testing and unit test coverage with each release candidate

• Investigate the relationship between Eddy Current Testing (ECT) signals and microstructural properties
• Detect latent patterns in ECT data that reflect intrinsic material characteristics
• Develop and validate predictive models for microstructural classification and quantification, using hardness and case depth as benchmarks
• Apply Bayesian Structural Equation Modeling for advanced data analysis

AI Readiness - Part 3: Creating an e-book on the use of AI in software testing

• Designed and created an e-book on the sensible and safe use of AI in software testing from the perspective of an experienced test expert.
• Used generative AI (ChatGPT, Perplexity Pro) as a sparring partner for structuring, wording suggestions and creating variations, with all content finally reviewed and approved using my own expertise.
• Developed practical insights into the opportunities and risks of AI in testing, with a special focus on collaboration between testers and AI instead of “tester vs. AI”.
• Title: “11 starke Gründe: Dream-Team statt Rivalen - Tester und KI sind gemeinsam unschlagbar”
• Subtitle: “Wie Mensch und Maschine im Softwaretest das perfekte Team bilden – und warum reines KI-Testing riskant ist.”
• Planned use of the e-book as a basis for workshops, customer meetings or internal training.
• Technology: Generative AI, ChatGPT, Perplexity Pro, Microsoft Word, Adobe Acrobat, many years of hands-on professional testing experience, common sense.

• Extension of a Swing-based UI for recording Security Restricted Articles during baggage screening.
• Introduction of a new workflow for recording Deboarding Events.
• Extension of the reporting system for Security Restricted Articles and Deboarding Events.
• Implementation using JBoss Wildfly, PostgreSQL, spring-boot 3.x, Java 8/21, Swing, JSF, JAX-RS/Resteasy, Docker, Maven, Kiro.

Project – Evaluation and development of databases for a new product line for a measuring equipment manufacturer

• Current-state analysis
• Requirements analysis of the data storage layer
• Writing benchmark tests
• Design of the new database schema
• Database migrations
• Development of audit logging and Part11
• Creation of backup and recovery concepts
• Design of the persistence layer API
• Writing unit tests
• Creating requirements in Azure

Tools: C#, Visual Studio 2022, Azure DevOps, SonarQube, Git, RestSharp, WebServer, PostgreSQL, MS SQL, SQLite, MinIO, Podman, Docker, DataGrip, SQL Management Studio, HeidiDB, pgAdmin

Working Environment

• Insurance / Claims Management (Property, Liability, Automotive)
• REST-based ClaimAPI with Guidewire ClaimCenter

Scope

• Further development of the internal REST-based ClaimAPI with Guidewire ClaimCenter as the backend and various portals/front-end offices as clients, and with the following objectives: + increased AI-supported claims processing outside of Guidewire ClaimCenter + and support for all lines (property, liability, automotive).
• Further development of automated claims processing

Activities

• Interfacing IT & Business
• Design activities with documentation in Confluence, Jira: + Requirements engineering (functional and non-functional) + Design of REST endpoints and coordination with interface partners (esp. AI-colleagues) + Identification, design and evaluation of alternative solutions (moving away from a monolithic approach toward fine-grained endpoints, with code reuse across all lines if possible) + Creation / refinement of product backlog items in Jira, i.e. epics, user stories and tasks, incl. alignment with developers & POs during (pre-)refinement sessions + Using AXA Secure GPT when creating / refining user stories (description, acceptance criteria) and designing REST endpoints + Estimation and prioritization of user stories and tasks during Sprint Planning sessions + Coordination and support during the implementation of Product Backlog items + Driving decision making with preparation and presentation of decision-making documents
• Quality assurance: + Test management, including test case creation using Xray in Jira + Test execution using Bruno as REST client and in Guidewire ClaimCenter + Submission of test artifacts for PO approval + Analysis of production bugs

Methods Big Room Planning (aka PI-Planning in SAFe), Scrum, BPMN, EPK, UML, ERM, DDD

Tools / Tech Stack Teams, Confluence, Jira with Xray, OpenAPI/Swagger, REST, JSON, XML, MS Office, Bruno, GitHub repository (reading), Guidewire ClaimCenter, AXA Secure GPT (AXA's in-house GenAI solution based on Azure OpenAI)

• Designed and developed a production-ready data platform based on Microsoft Fabric for an e-commerce company
• Built a scalable Medallion Architecture (Bronze, Silver, Gold) with Lakehouse and Delta Lake as the foundation for analytics and AI applications
• Developed a metadata-driven ETL platform with PySpark and a generic Incremental Loading Framework (SQL Server → Bronze → Silver → Gold)
• Developed reusable components for Microsoft Fabric Notebooks to standardize data integration, transformation, and validation
• Implemented automated data pipelines including monitoring, logging, error handling, and Delta MERGE strategies for stable production operations
• Built a business layer architecture for reporting, data warehousing, and reusable data products
• Integrated heterogeneous data sources via SQL Server, REST APIs, Amazon SP API, and Google Analytics 4
• Worked closely with business departments to analyze business requirements and translate them into scalable data architectures

Technologies: Microsoft Fabric, PySpark, Python, SQL Server, Delta Lake, Lakehouse, OneLake, Data Factory, Data Warehouse, REST APIs, Amazon SP-API, Google Analytics 4

• Built a data integration platform for high-, medium- and low-voltage assets to enable contextual analysis of time series with master data from SCADA control systems (IEC 60870 104), INIS and SAP.
• Responsible for the architecture and implementation of the solution, and acted as a sparring partner for the Product Owner.
• Technologies used: Kotlin, Spring Boot, Maven, TimescaleDB, PostgreSQL, liquibase, Elements IoT, Docker, Kubernetes, Grafana, Python, jupyter and various API gateways.

Further Development of the Integrated Capacity Management Platform InKa

Rail Infrastructure

• Power BI shared datasets and reports via DirectQuery on Amazon Redshift (timetable, construction and capacity data)
• Automated report testing with Playwright in Docker containers, version control with GitLab
• Concept and implementation of user communication (information page, changelog, known bugs)

Initial Situation:

The integrated capacity management platform (InKa) is a monitoring and analysis platform for data from timetable and capacity management: customer orders, infrastructure, timetable operations, construction, as well as route capacity and width. The data is stored and linked in a structured data warehouse. This makes it possible to create complex KPIs across different source systems and display current and future route utilization as well as construction activity across the network. The goal is to improve strategic, medium-term and intra-year planning and provide users with easy access to capacity management analyses.

Measures:

• Enablement: Introduction of Power BI with training and workshops for development teams.
• Consulting & Design: Problem analysis, concepts and solution consulting for reporting requirements; implementation of reporting solution plans.
• Data Model: Development of shared datasets with DirectQuery on Amazon Redshift and import tables; DAX measures for utilization and capacity KPIs.
• Development: Data analysis, data transformation and visualization in Power BI; extension and migration of business applications to Power BI; AI-supported development in VS Code with GitHub Copilot.
• Test Automation: Automated testing of Power BI reports with Playwright; setup of the test environment in Docker containers.
• User Communication: Concept and implementation of a central information page with hot news, changelog and known bugs, access from reports with report filters, updates via Power Automate.
• Deployment: Management of Power BI Deployment Pipelines across the DEV, TEST and PROD environments.
• Agile Working: Work in an agile team according to SAFe (Scaled Agile Framework); refinement of user stories and features including effort estimates in Jira; version control with Git and GitLab.
• Quality & Documentation: Reviews for quality assurance, error analysis and resolution, technical documentation in AsciiDoc and Confluence.

Technologies: Power BI, DAX, Power Query, DirectQuery, Amazon Redshift, Git / GitLab, Deployment Pipelines, Playwright, Docker, AsciiDoc, Power Automate, Jira, Confluence, VS Code with GitHub Copilot, SAFe

Results:

• Capacity management KPIs from multiple source systems combined on one platform
• Transparency regarding current and future route utilization and construction activity across the network
• Easy access to analyses for users
• Automated regression testing of Power BI reports
• User communication implemented: central information page with hot news, changelog and known bugs, directly accessible from the reports

• Optimized the data architecture (Medallion) to better decouple processing steps and improve transparency and reproducibility

• Ensured the technical quality of data processing in Databricks by introducing schema enforcement, data quality checks, and a structured data architecture

• Pipeline orchestration with Azure Data Factory

• Improved and automated the development and deployment process by integrating Git and GitHub Actions

• Technical leadership of the Data Engineering team (3 employees)

• Led workshops to optimize and stabilize the data platform and development process

• Collected and prioritized new requests and maintained the product backlog

• Technologies: Microsoft Azure (Data Lake, Data Factory), Databricks, Apache Spark (PySpark), Python, SQL, Git, Confluence, Power BI, Power Apps, Dataverse, MS Sharepoint, Mural

• Development of scalable backend applications with C#/.NET and Java
• Design and implementation of distributed microservice architectures
• Development and integration of REST APIs for industrial applications
• Development of modern web applications with React, Angular, and TypeScript
• Implementation of MQTT-based communication solutions
• Integration of industrial protocols such as OPC UA and Modbus TCP
• Development of batch, process control, and HMI components
• Containerization and deployment of applications with Docker
• Conducting code reviews and supporting architecture decisions
• Close collaboration with Product Owners, QA, and interdisciplinary teams
• Analysis of business requirements and implementation of technical solutions
• Further development of existing software architectures with a focus on maintainability and performance

Technologies: C#, .NET, ASP.NET Core, Java, C++, React, Angular, TypeScript, Vue.JS, MQTT, OPC UA, Modbus TCP, Docker, GitLab, MariaDB, MySQL, Linux

• Architected an enterprise Fabric-based data-product governance framework, authoring data contracts and schema-validation KPIs to enforce completeness, freshness and SLA standards across reporting data products.
• Operationalized pipeline observability by integrating Dagster orchestration data into automated data-health reporting, proactively validating data integrity and pipeline reliability before production reporting layers refresh.
• Established BI-as-Code and end-to-end governance through Git-based version control, CI/CD and Alpha→GA release management, strengthening lineage, schema-drift detection and production change traceability.

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.