Camunda Expert

AI phone assistant platform

Claude Code, Google AI Studio, Python, LLM / Voice-AI, PostgreSQL

• Designed and hands-on developed an AI-powered phone assistant platform (Voice-AI / LLM)—from idea and architecture through to MVP/product.
• Built agentic workflows and end-to-end automations with Claude Code and Google AI Studio.
• Also supported AI-powered delivery in client engagements: using Claude Code for governance documentation, requirements drafts, and automations.

Led the end-to-end integration and migration architecture for decommissioning SAP IS-U market communication and transitioning to Salesforce Marketing Cloud (SFMC) with E.ON IT Services — covering regulated EDIFACT market messaging, a three-phase data migration (transfer of market message inventory after cutover), redesign of market communication processes, and full GDPR and German energy-market compliance.

• Designed the three-tier target architecture (SAP IS-U → NScale B2B gateway → SFMC) processing 50,000–100,000 EDIFACT messages daily within sub-5-minute SLAs.
• Architected the three-phase data migration: 36 months of historical data, zero-loss cutover of in-flight market messages, and near-real-time CDC synchronization.
• Delivered secure, BDEW/GDPR-compliant integration (AS2/OFTP2, RFC/IDoc, REST APIs, OAuth 2.0, Azure AD, AWS S3) achieving >99.5% uptime, <0.1% migration discrepancy, and RTO <4 hours.
• Applied BPMN to model and optimize the market communication processes.

Technologies: SAP IS-U, NScale, Salesforce Marketing Cloud, EDIFACT, OAuth 2.0, Azure AD, AWS S3, BPMN, Jira, Confluence, Draw.io

• Documented complex financial reporting processes in deep-dive sessions with subject matter experts
• Analyzed and mapped the 3-tier data flow SAP – Essbase – HQ (984 account entries, triple chart of accounts)
• Identified the biggest time drains (40 % of close time)
• Evaluated technologies (AWS, Microsoft Fabric, Custom/Hybrid) with cost-benefit analysis
• Created a validation rule catalog with 351 rules as the basis for pre-submission automation
• Business case: estimated savings potential of 480–960 T€/year for the EAR region
• Hands-on implementation with Microsoft Fabric, RAG, AI agents/Tool Calling and n8n; productive use of Microsoft Copilot and Copilot Studio
• AI-supported project management workflows (minutes, tasks, knowledge synchronization)
• Stakeholder management at senior management level (EAR Accounting, IEA IT, TFSC Japan), workshops and training on AI tools

Technologies: Microsoft Fabric, Copilot Studio, Claude AI, Python, Power BI, SAP, Essbase/SmartView, Excel (VBA), Notion, SharePoint

Design, development, and market launch of digital products and platforms – from strategic alignment and agile implementation to Go-to-Market and Go-Live, integrating AI into processes and products

• Industry: Insurance, Trade, IT
• Customers & Projects: Consulting and selling insurance and similar services
• Main tasks: Insurance consulting (health insurance, retirement planning, wealth building); commercial services, inside and field sales; sales data analysis and forecasting; customer consulting and support; opening a new sales headquarters for private and business customers; business development & innovation management; business use case development; process optimization; stakeholder management; team leadership and training; preparation and delivery of trainings;
• Technologies used: Microsoft Office 365, Microsoft Teams, Jira, Draw.IO, Camunda 8, Java (8, 17,21,25), Git, Spring Boot, Spring Batch, Spring Data REST, Spring Web, Spring Security, J-Unit, Playwright, Lombock, Vaadin, H2, PostgreSQL (16, 17 18), pgAdmin, Docker, LLMs, JasperSoft Studio, JasperReports

• Development of an agent-based governance platform for the automated assurance of EU AI Act compliance and ODA-compliant orchestration of AI services in complex enterprise environments.

• Design and implementation of an agent-based "Mission Control" framework (Aletheia Conductor) for autonomous state monitoring and process control.

• Development of "Compliance-as-Code" (CaC) solutions based on OPA/Rego for system-wide enforcement of regulatory guardrails.

• Integration of TM Forum ODA standards (TMF630, TMF622, TMF642) to ensure interoperability and standardization.

• Building a highly available event-driven architecture using Redpanda and CloudEvents v1.0 for near-real-time event processing.

• Implementation of an audit-proof "Evidence Chain" through cryptographic linking of trace logs in preparation for automated audits.

• Tech Stack: Java 21 (Quarkus Native), TypeScript (Next.js), Redpanda (Kafka API), CloudEvents v1.0, OPA (Open Policy Agent) & Rego, TimescaleDB, ZincSearch, Redis, TM Forum ODA, Git, GitHub, Clean Code Development, Like-C4.

Project overview: The use of “Generative Pretrained Transformer” (GPT) technologies will greatly change the world of work in the coming years. ITZBund is developing a basic service for this purpose, which can be used by its 200 customers. This basic service is offered both on-premises and in the cloud. Launched in 12/23, production systems (based on the MVP) had already been successfully rolled out and operated for several authorities and federal ministries by 05/24.

Project metrics:

• 2024 budget approx. 20 Mio €
• approx. 70 people directly involved in the project
• regular (indirect) contact with approx. 80 people in the wider project environment

My main responsibilities:

• Overall responsibility as external project manager
• Project definition phase/ Project setup and establishment of the project organization
• Strategic and operational project planning, as well as project design and ongoing adjustments
• Ongoing coordination with the project owner and stakeholders at ITZBund
• Ongoing coordination with sub-project managers, agile roles, and other project team members
• Responsibility for project controlling, quality management, risk management, and change management
• Responsibility for providing the basic service in on-premises and cloud environments and its ongoing development
• Planning and leading several hypercare phases
• Collaboration and ongoing coordination with a federal ministry partner project and delivery of an MVP
• Coordination with the agile teams
• Coordination with operations, release, and deployment
• Responsibility for delivering initial customer projects
• Responsibility for developing AI governance
• Ensuring accessibility (BITV)
• Responsibility for setting up a sub-project for marketing activities
• Support in setting up an efficient proposal process
• Stakeholder management

Approach:

• V-Modell XT ITZBund
• Scrum

Tools used:

• Microsoft Office, Skype, MS Project, Confluence, Jira, Sharepoint, Miro

Project: Introduction of statutory-compliant electronic invoicing (outbound, Germany) in SAP for an international technology group.

• Project management: Planning, steering and reporting of the E-Invoicing outbound rollout across all affected business areas, including budget and resource coordination.
• UAT: Structured user acceptance test with key users per business area, test cases per invoice scenario, and consolidated test results for decision making.
• Defect management: Handover and tracking of defects in Jira, including validation of the generated invoices against the statutory schemas.
• Cutover, go-live and hypercare: Readiness checks and cutover planning aligned with the statutory deadlines, coordination of go-live and stabilization during hypercare.
• Stakeholder management and reporting: Alignment with Finance, Tax, business departments and IT, preparation of status reports and decision papers, and consistent follow-up of open items.
• Change management and documentation: Communicated process changes to the business departments, enabled key users, and created process and compliance documentation to ensure traceability and audit readiness.

• Fully on-premises LLM document-examination platform for a compliance-critical banking domain: agentic LangGraph pipeline with deterministic verification, every AI judgment structured and source-anchored; ~960 automated tests, zero data egress
• GPU throughput engineering (quantized serving, speculative decoding, prefix caching): 9.5x extraction speed-up, 500+ multi-document case files per day on a single A100
• AI-native EDI/EDIFACT integration platform (~116k LOC Java 25 / Spring Boot 4, 1,900+ tests): LLM-drafted partner mappings machine-verified before go-live (DFDL conformance, field-coverage checks, dry runs), ~99.5% byte match on real customer files — replacing weeks of manual mapping per partner

• Designed a migration strategy for WLS applications to BKA Cloud and Stack IT

• Created a hybrid cloud for internal testing and development with Kubernetes

• Transformed the IT landscape from an outdated monolithic architecture to a cloud-based architecture

• Integrated new CI/CD processes using Azure Pipelines

• Quadrupled the processing throughput for personnel security checks

• Migrated personnel security screening applications to Docker-based applications

• Implemented CI/deployment pipelines using Azure DevOps

• Environment: Java Springboot, Kubernetes, Oracle Weblogic, OpenID, Camunda, JUnit, TOGAF

• Developed critical specifications, navigating technical and business requirements.
• Led the project through its complex phases.
• Orchestrated and supported the Integration Testing Cycle (ITC) and User Acceptance Testing (UAT).
• Implemented robust test methodologies and systematically documented and addressed findings contributing to pre-GoLive readiness.
• Ensured flawless implementation and enabled effective trainer training.
• Conducted unit and functional tests.
• Facilitated alignment between development and business goals.
• Provided transparent progress reports and maintained documentation quality.
• Developed Fiori apps for inventory management and material staging status.

• Led QA and test automation for a distributed industrial IoT and data-integration platform connecting shop-floor systems with enterprise applications.
• Designed and maintained automated API and UI tests using Playwright, TypeScript, and Python, covering REST APIs, authentication, resource management, integrations, permissions, and end-to-end workflows.
• Tested distributed services, data pipelines, messaging infrastructure, containerized applications, and integrations across Kubernetes, OpenShift, Docker, and Docker Compose environments.
• Performed functional, integration, regression, endurance, resilience, load, chaos, and exploratory testing across complex distributed systems.
• Used Chaos Mesh and Toxiproxy for network fault injection, latency, packet loss, and partition scenarios to validate system resilience and failure handling.
• Automated infrastructure provisioning, configuration, and environment setup with Ansible and managed deployments using Kubernetes and Helm.
• Tested integrations with industrial protocols, messaging systems, databases, HTTP/REST APIs, and external enterprise systems using simulators, emulators, and dedicated test environments.
• Worked with MQTT, Kafka, SQL databases, InfluxDB, REST APIs, OAuth 2.0, JWT, LDAP, Active Directory, OpenLDAP, mTLS, TLS, MFA, SSO, and RBAC.
• Investigated and resolved 40+ defects across backend services, integrations, distributed components, and web applications, using AI-assisted analysis with Claude to accelerate debugging, test design, and root-cause investigation.
• Improved deployment reliability through Kubernetes/OpenShift configuration and health-check tuning and monitored distributed systems using Grafana, Prometheus, and Loki.
• Collaborated with developers and product teams on sprint planning, technical refinement, quality strategy, release testing, and continuous improvement.
• Applied AI-assisted and agentic testing approaches to expand automated coverage and identify complex edge cases.

• Implementing and extending an Electron app based on TypeScript, React and Node.js to display stream content and technical data
• Extending a Kotlin backend for message processing via Kafka
• Extending various React modules
• Programming custom solutions for customers, including testing
• Creating documentation
• Development in accordance with Scrum processes

Used skills: React, React Hooks, Jest, Vitest, Typescript, Electron, IntelliJ, Vite, Github, Jira, Node.js, yarn, npm, pnpm, Swagger, OpenAPI, Storybook, Docker, Prettier, Eslint, tailwindcss, i18n, GraphQL, CoPilot, Postgres, JSON, Sqlite, trpc, influxdb, Java, Spring, Kotlin, Kafka, Git, Sonarcube