GitHub Copilot Experts in Munich

• Governed multi-agent orchestration for regulated, EU-based companies – self-hostable, compliant with the EU AI Act and GDPR („by design“), BYOM (own models/GPU).
• Two-gate governance: agent deliberation + mandatory human approval, complete signed audit trail; graduated autonomy model („internal → autonomous per skill“).
• Verified knowledge graph („Company Brain“) with source evidence for each answer; proprietary orchestration framework (Virtual Team Framework).
• Industry solutions for financial services: compliance monitoring, invoice and contract review; hands-on development with LLMs (including Anthropic/Claude), agentic workflows, RAG.
• Development of the governance-focused multi-agent platform TeamIntel (see AI reference projects).

Worked as an App Engineer as part of the IoT Control team in a React Native Stack.

• Implementing new Components based on the Tonies Design System.
• Improving, extending and maintaining Tonies Design System
• Adding new features like Volume and Playback Control of the Tonies
• Fixed connection issues via bluetooth and wifi
• Removing technical debt and polishing for an upcoming big software and hardware release
• Improving accessibility by optimizing screens and components for usage via screen readers.
• Wrote lots of automated tests to ensure app quality is always stellar.
• Weekly app releases in a high volume workload environment

Results & Impact:

• Improved app stability and connection reliability ahead of a major software and hardware release
• Raised overall app quality through a significantly broader automated test suite, catching regressions before they reached users
• Made the app usable with screen readers, improving accessibility for a wider audience
• Sustained a weekly release rhythm in a high-volume production environment without quality regressions

Technologies: react-native, expo, typescript, react-19, react-compiler, react-navigation, zustand, @tanstack/react-query, i18next, figma, app-store, play-store, sentry, bitrise, config-cat, poeditor

• Agile development of a multimodal analysis platform for training materials (video, audio, documents) using Scrum
• Extraction of context-relevant content based on user profiles & competency dimensions
• Personalized delivery of learning content to improve sales performance
• Close coordination with sales teams & stakeholders to validate features
• Use of Gemini, Whisper, Python & JavaScript, deployment on AWS, Perl for scripting data imports
• Integration into existing tools & CRM systems for smooth adoption
• Technologies used: Python, OpenAI, DB tech such as PostgreSQL, CI/CD for AirFlow DAGs, FastAPI

• Further development of the internal "ECockpit" platform with an Angular 17 frontend and .NET (C#) backend
• Maintenance and further development of Azure DevOps pipelines
• Introduction of technical improvements in build & release processes
• Collaboration on a modular architecture approach (Clean Architecture & DDD)
• Focus on scalability and secure data processing
• Tech stack: Angular 17, .NET / C#, Azure, Azure DevOps, Git, CI/CD, Clean Architecture, Domain Driven Design

• Software development of a B2B SaaS for AI-based search in internal candidate pools of recruitment agencies
• Design of a multi-tenant, hybrid architecture with dedicated GPU servers and secure cloud integration
• AI-Engineering
• LLMOps
• Python
• FastAPI

• Evaluation of RAG for legal advisory (build or buy)
• Evaluation and POC of RAG for an ERP time tracking module
• Consulting on foundation model selection
• Setup AI development environment (eliminating shadow AI)
• AI strategy consulting
• AI-assisted code creation and context engineering make change sets larger
• Strong software engineering expertise, code reviews and safeguarding through pipelines and domain-specific automated test cases

• Platform: Python ecosystem, RHEL 8, K10, AWS IoT Core, AWS Lambda, MLOps
• Software: Java JEE/cloud, IntelliJ IDEA, AWS IoT Core, AWS Edge and Lambda, AWS SageMaker SDK, Docker Compose, Kubernetes, OpenShift 4, Tekton, Flux, Helm charts, JSON/XML technology, Nginx, Apache Spark, OpenAI (GPT Plus, DALL-E 3, Whisper), GAN, GitHub Copilot, AI/machine and deep learning, Jupyter notebooks, TensorFlow 2, Colab, Keras API, Prometheus, Grafana, Conda, Python 3.9, PySci stack (NumPy, pandas, Scikit-learn, matplotlib)
• Responsible for webinar:
• IoT edge computing: architecture, components, resources, management
• IoT edge computing with MicroK8s, designing and creating flows/diagrams for AWS, three-step model for IoT ecosystem
• IoT processes, connectivity, data transfer and deployment, security
• Optimization of edge computing for IoT networks and services (AWS SQS queue, SNS notifications, events, analytics, buttons, device management/defender, Things Graph)
• Machine/deep learning frameworks (models, training, pipeline optimization, deployment in the cloud/at the edge (OpenShift), monitoring workloads with Prometheus and Grafana)
• Performance optimization for low latency/resilience using adaptive ML/DL/RL models for customer IoT data
• Analysis of large sensor data sets with Apache Spark, Kafka clusters
• Kasten K10 data management platform on Kubernetes multi-cluster with Helm chart, deployment, backup/disaster recovery (RTO/RPO), data lifecycle and security management
• Implementation of multilayer artificial neural network (ANN) with TensorFlow 2 and Colab for regression and classification; data analysis and provisioning for applications; development of models for testing and training, deployment of models
• Automation of business streamline processes with AI (Azure OpenAI, Discord bots/Zapier apps AI assistants (IntelliJ, GitHub Copilot))

As part of an in-house development project, a pipeline for automated lead generation was created as the second stage of a preceding system for project monitoring. Based on a list of freelance project URLs (freelancermap), qualified lead records are generated, including company, contact person, official and personal email address, and the appropriate form of address (informal/formal). The technologies used were Python (openpyxl, requests) as well as an LLM agent workflow in VS Code (GitHub Copilot Chat) with a custom slash command and extensive rule set; search APIs (Serper.dev) are connected for research. My tasks included the full concept and development. The core is a rule set of around 480 lines that guides the LLM agent deterministically through extraction, website and email lookup, duplicate matching (against existing provider lists), and the creation of a structured JSON output. Deterministic steps (Excel matching, web/email search, pattern derivation) were moved into Python helper scripts. Other requirements included validating the results through versioned blind runs against a reference, iterative refinement of the rule set, and a swappable search provider layer for cost and stability reasons.