Linux Experts in Berlin

• Designed, built, and launched an internal event planning web application used by over 100 department leads for a large event, despite having no dedicated testing phase.

• Ensured smooth, failure-free operation during first production use, leading to the tool being adopted for future events.

• Automated catering calculations and related workflows, significantly reducing email communication and manual computation effort for meal planning.

• Managed deployment and hosting on a Linux server using Coolify, including application setup and runtime operations.

• Hired and guided a communication designer on UX while independently owning all technical decisions and implementation.

• Converts natural language into JQL using RAG and pgvector. Returns structured JSON with a query, chart spec, and plain-text answer. A two-stage router answers general questions without touching the JQL pipeline at all.
• Interchangeable LLM backends: Ollama, vLLM, Groq, Anthropic Claude, AWS Bedrock - switchable at runtime, no code changes. Self-healing JQL: on Jira validation failure, feeds error back to LLM, retries up to 4 times. OCI Vault for secrets. Deployed on Oracle Cloud A1 with GPU inference over Tailscale private network. Open source.

• Designed and implemented a hybrid recommendation system (content-based + collaborative filtering)
• Built end-to-end ML pipelines including data processing, feature engineering, model training, and evaluation
• Developed RAG-based LLM systems using LangChain and vector databases for semantic search and knowledge retrieval
• Established MLOps workflows with MLflow for experiment tracking, versioning, and deployment readiness
• Implemented deep learning models (computer vision & classification) using PyTorch and TensorFlow

• Add/create test specifications
• Conduct regression tests
• Conduct release tests
• Analyze Jira tickets
• Identify software defects and fix them with C#

• Codebase Evaluation & Problem Design: Designed and stress-tested complex software engineering problems against large open-source Python codebases (including pandas), requiring deep context acquisition and architectural understanding to produce well-scoped, realistic problem statements aligned to strict correctness guidelines.
• Agent Failure Analysis: Assessed LLM coding agent solutions for correctness and completeness, identifying meaningful failures across edge case handling, dtype behaviour, and multi-column NaN propagation logic; documented findings with precision for downstream evaluation use.
• Programmatic Test Suite Development: Authored comprehensive pytest suites to programmatically verify agent-generated solutions against defined requirements, with deliberate coverage of boundary conditions and failure modes not caught by naive implementations.
• Containerised Environment Engineering: Built and debugged Docker environments for reproducible agent execution, including git-based repository provisioning, dependency pinning with npm ci, and multi-stage Dockerfile authoring across Linux-based containers.

• Providing freelance software engineering and AI orchestration services for an early-stage startup.
• Designing and coordinating autonomous AI systems capable of executing complex, multi- step workflows.
• Developing customer-facing pilots and proof-of-concept solutions.
• Participating in meetings with customers and investors to support product development and business discussions.

• Acted as technical consultant to optimize multi-layer ensemble models combining ResNet, CNN-BiGRU-Attention, and XGBoost.
• Guided implementation of a Logistic Regression meta-learner to solve class imbalance problems, achieving 92.86% accuracy and 0.9644 AUC on PTB-XL and Chapman-Shaoxing datasets.

• Replacement of a RIS and PACS system in combination with three different software solutions, with a focus on redesigning and further developing existing processes.
• Ensuring the interaction of the individual solutions and their integration into one overall solution to provide optimal support for medical staff in their daily work.
• Overall project management including coordination of three service providers.
• Use of technologies and solutions such as RIS, PACS, Smart Reporting, and Artificial Intelligence.
• Leading the RIS & PACS replacement in a hospital.
• Support with the communication strategy.
• Coordination of external and internal resources.
• Stakeholder management.
• Steering of steering committees.

• Work within time-critical operating procedures; coordinate issues with customers, partners and central support.
• Maintain reliable handovers and concise incident communication when service, equipment or routing issues occur.

• IT training in theory and practice for IT specialists in application development and system integration

• Mobile Device Management (MDM) for iOS devices (iPads, iPhones)
• Management, configuration and rollout of policies, apps and security measures
• eSIM setup & management as well as management of mobile plans and contracts
• User management (create, block, delete) in the SecurePIM security solution
• Device registration, preparation and setup of devices with Windows 10/11 and peripherals
• 1st & 2nd level support and handling of IT requests via the ticket system
• Troubleshooting, fault isolation and repair of devices
• Creating and maintaining guides, training new users and handling user questions

PCB design with Altium, MCU Programming, Prototyping

• Insurance service provider*

Challenge: Business-critical documents were processed through external OCR providers, with ongoing costs, dependency, and data privacy risks for sensitive insurance data.

Implementation:

• Architecture and production implementation of an on-premise OCR solution with full data ownership
• Methods for recognizing document structures as the basis for automated further processing
• ML-, NLP-, and LLM/VLM-based information extraction, especially from invoices and quotations

Success: Replaced external providers: full data ownership, GDPR-compliant processing, and 75% lower recurring OCR costs per year

Used technologies: Python, Docker, Microservices, FastAPI, PyTorch, Torchvision, MongoDB, MySQL

• Manage the development release and update process for a digitized nationwide trade register project "AuRegis".

• Support software in Kubernetes/OpenShift environments, configure management with Kustomize, and implement CI/CD pipelines using Jenkins/GitLab, SonarQube, ArgoCD, and Azure.

• Oversee system release of microservice architecture.

• Craft the CI/CD stack from scratch with GitLab CI, integrating integration tests, dependency checks, and security measures.

• Automate deployment onto OpenShift using Kustomize.

• Establish infrastructure components for development, code review, and code quality analysis including SonarQube.

• Integrate GitOps tools such as Kustomize and ArgoCD, leveraging both Azure and private cloud for sensitive data handling.

• Develop Python scripts in Jenkins for cryptostore configuration and system packaging of products and microservices into deployable units.

• Automate delivery to customers and deployment on test systems.

• Craft Kustomize manifests for microservices and develop accompanying automation, treating documentation as code for clarity and reproducibility.

• Serve as technical advisor for the project's first go-live and oversee further deployments as technical rollout manager.