Cloud Native Experts in Hamburg

traigo is VTG's digital rail logistics and fleet management platform. It processes large volumes of telemetry, mileage, geofence, sensor and wagon-movement events in near real time and provides operational services for rail logistics customers across Europe.

As part of Team Customer Selfcare, I worked on the design, implementation, optimisation and operation of large-scale backend services and event-driven processing pipelines — covering both feature development and operational ownership of business-critical production systems. I also regularly acted as first responder for production incidents, data inconsistencies and performance investigations across multiple distributed services.

• Design and implementation of event-driven backend services.
• Migration and replacement of legacy processing pipelines.
• Development of replay / rebuild mechanisms for large event datasets.
• High-throughput asynchronous event processing on SNS / SQS.
• Database and query optimisation for PostgreSQL and DynamoDB.
• Design of scalable read / write models and aggregation pipelines.
• Production troubleshooting and operational support.
• Performance tuning and infrastructure scaling.
• Design and stabilisation of integration and system tests.
• Technical concepts, architecture documentation, and cross-team collaboration.
• Support the further development of existing GitLab CI/CD pipelines

Geofence & Wagon Stay Processing

• Algorithm to detect vehicles within geofences (entry, exit, dwell time).
• Event sourcing with guaranteed chronological order within the affected time window.
• Refactored geofence event and wagon-stay processing logic for performance.
• Resolved race conditions and event-ordering problems in distributed services; server-side filtering, aggregation and optimised query pipelines.
• Repair and replay tooling for corrupted or inconsistent movement data.

Fleet Metadata & Mileage

• Modernised the service; migrated storage from DynamoDB to PostgreSQL to improve traceability and accelerate new features.
• Scalable mileage aggregation and replay mechanisms.
• Read / write models and optimised queries for high-volume mileage calculations.

Sensor & Telematics Integration

• Integrated telemetry and sensor processing pipelines.
• Snapshot and state-calculation logic for sensor systems.
• APIs and persistence models for wagon sensor data; data-quality improvements.
• Further development of a service using gRPC for intra-service communication.

Movement Segment Processing & Routing

• Migrated services to new movement-segment event streams.
• Built replay and rebuild tooling for segment correction.
• Optimised throughput and reliability for high-volume event processing.

Condition Monitoring & Wagon Analytics

• APIs and backend services for wagon condition monitoring.
• Brake-wear prediction processing and wagon analytics functionality.
• PostgreSQL views and optimised query models for operational dashboards.

Operational Reliability - First Responder

• Investigated production incidents and distributed-system failures; DLQ analysis, replay and operational recovery.
• Tuned database performance and AWS infrastructure under production load.
• Improved observability, monitoring and operational tooling.
• Supported rollout strategies, monitoring and post-deployment stabilisation.

I implemented a Zero-Trust architecture for robust, military-grade maritime container mini data centers based on VMware & Tanzu to support containerized GIS workloads for ground forces. The main focus was on securing communications, workload protection, and data access in contested electronic battle environments affected by jamming, interception, signal manipulation, and constantly changing operational conditions. I designed and architected use cases so that every element of workload, identity, and system could continue to operate independently and securely even in degraded or disrupted scenarios. In parallel, I defined the enterprise and solution security architecture with LeanIX, Bizzdesign, and HOPEX as enterprise architecture, repository, and governance platforms to maintain architecture inventory, relationships, traceability, target pictures, and security governance in complex environments. For the architectural designs, I used Sparx Enterprise Architect to describe formal architecture views, interfaces, trust boundaries, and system architecture in both IT and OT environments. IriusRisk was used for threat modeling of the solution to identify architecture-driven risks, derive security requirements, and detect countermeasures and design gaps directly from the solution models. Risk and compliance management was supported with Archer. Architecture decisions, control gaps, and operational risks were translated into controlled governance and auditable compliance measures. For documentation, collaboration, and visual design, I used Confluence to maintain Architecture Decision Records, Security Blueprints, and workflows. I used Lucidchart and draw.io to create design artifacts tailored to stakeholders. I also defined OT security concepts with support from electrical and mechanical engineers in the areas of oil, vehicle onboard systems, rail, power plants, pharma, gas turbines, and nuclear technology. I created the end-to-end OT security strategy, starting with global policy, developed into standards and procedures, and finally aligned with Bell-LaPadula, Purdue Model, SABSA, TOGAF ADM, CENELEC 50701, IEC 62443, and NIST standards. In addition, I worked with engineering team leads to identify critical KBP assets and place them under protective measures that segmented SCADA, PLC, and HMI assets. I drove collaboration between Security, IT, and OT teams to create standardized workflows and use cases for the OT security solution catalog, while integrating Defense-in-Depth and Zero-Trust principles into operational environments. A key part of my work was integrating multidisciplinary engineering, security, and operations stakeholders into a unified security blueprinting strategy and ensuring that architecture, threat modeling, governance, and documentation were technically strong and operationally practical.

• Several projects in a police context
• Model and document police procedures/projects with Archimate (as-is/to-be) in the context of P20 (BKA)
• Create software architectures with microservices
• POC development with Springboot/Docker/Kubernetes
• Project size: 10 people
• Enterprise architecture management with Togaf and Archimate
• Backend software development Springboot
• DevOps with Kubernetes
• Implemented using: Java 17/21, Springboot 3, P20 architecture, Togaf, Archimate

• Lead developer of Prof. Valmed, the first LLM-powered medical device (utilising RAG on a medical corpus of 2.5M+ documents) to receive a CE certification.
• Designed and implemented cloud-native MLOps infrastructure for ENBW’s energy trading analytics division, enabling scalable deployment and monitoring of predictive models.
• Architected end-to-end testing and validation frameworks for AI/ML systems, ensuring quality, compliance, and robustness in critical and regulated applications.
• Conducted professional training on AI testing, EU regulatory frameworks, and quality assurance for production AI systems.

• Directed a 110-strong global team including data scientists, product managers, sales, operations, and developers
• Led investment and strategic reviews of scale-up ventures to drive profitability
• Developed and implemented portfolio strategy focused on IoT, AI, API platforms, and software products
• Restructured portfolio, eliminating unprofitable products and reallocating 70% of investments and resources to AI and platform development
• Delivered Vodafone’s first internal GenAI projects, enhancing sales and marketing efficiency
• Streamlined innovation strategy, reducing initiatives by 80% to focus on AI product enhancements and network APIs

• Extended the document management system with a standard CMIS (Content Management Interoperability Services) interface
• Implemented CMIS core services like navigation, access rights, search, CRUD operations, and versioning in Java
• Implemented based on RESTful / OpenAPI services
• Delivered as a fat-jar and native container image
• Deployed on-premises and serverlessly as an Azure Container Application using Terraform
• Improved team autonomy through infrastructure engineering and short feedback loops
• Established observability with OpenTelemetry, Azure Monitor, and Azure Logic Apps
• Introduced Terraform and trunk-based development processes
• Ensured quality with BDD tests in C# using SpecFlow and Testcontainers
• Created Azure DevOps pipeline integration tests
• Introduced cloud deployment processes
• Trained staff in cloud and Terraform