IT Consultants in Munich

Designed a global SD-WAN / SASE solution (Paloalto Prisma Access or Cisco Secure Connect) and integrated it with the data center infrastructure (Cisco ACI, Cisco Catalyst/Nexus Switches, Cisco WLAN Controller, Cisco ISE)

• IT Sourcing & Carve-out: RFP management for IT client hardware and services as part of the Rheinmetall carve-out.
• Contract Management: Drafting of MSAs and SOWs taking into account AVB, BVB and LSA as well as Service Delivery Contracts.
• Vendor Transition: Strategic transition management to replace legacy contracts and establish new supplier relationships.
• SaaS Procurement: Negotiation of SaaS license agreements based on TCO and cost-effectiveness analyses.
• KPI: On-time transition of all 12 global group contracts, achieving 18 % cost savings on the IT hardware basket and 20 % cost avoidance for SaaS licenses – measured against the critical carve-out project plan and achieved through structured transition management.

AI Assistance and Target Vision for Partially Autonomous Energy Portfolio Management

Building an AI control layer directly on the up-to-date daily live portfolio of a large energy provider — not as an isolated pilot, but as an operational extension of the existing DB1 and portfolio management. The goal is the gradual development from assistance through monitoring/alerting to analysis agents with Human-in-the-Loop approvals, supplemented by a role-specific System of Engagement alongside the BI System of Record. At the same time, the business case, target vision and management pitch compared with static monthly reporting are being developed.

• AI control layer: Design and build on the existing live portfolio data product (several million contracts) — development stages assistance → monitoring/alerting → agents with Human-in-the-Loop approvals.
• LLM-supported data analysis: Semantic queries, SQL/tool integration and additional RAG components based on portfolio, plan-versus-actual and data quality data (Azure OpenAI, Snowflake), with drill-downs to individual contract level.
• Analysis agents: Multi-stage agents for variance and driver analyses of churn, price adjustments, volumes and procurement costs.
• Views concept: Role-specific interfaces for business units, management and C-level as a System of Engagement alongside the BI System of Record.
• Business case & pitch: Target vision and cost-benefit argumentation compared with static monthly reporting.
• LLM setup (privacy & security): Coordination with IT Security and Data Protection — EU region, data separation and approval processes.
• Agent architecture: Multi-stage agent pipelines (analysis → validation → summary) with documented data sources, tool calls, review steps and source references for each statement.
• Data foundation: Built on the up-to-date daily DB1 data product (Snowflake, dbt) — portfolio, plan-versus-actual and data quality metrics as the common basis for all AI analyses.
• Guardrails & evaluation: Evaluation and approval processes for LLM responses relating to management-relevant statements — test sets, metrics and human review.
• Prototyping & validation: Iterative validation of agent responses with the business unit — test question catalogue, feedback loops and response quality for each release.
• Roadmap & development stages: Detailed stages from assistance → monitoring/alerting → partially autonomous management, including transition criteria and governance for each stage.
• Integration: Integration into the existing BI and data landscape — BI remains the System of Record, while the AI layer provides interactive drill-down paths as the System of Engagement.
• Enablement: Enablement of business users — prompting guides, training and an operating model for ongoing use.
• Management: Coordination of business units, Data Engineering, IT Security and Data Protection.
• Change Management: Communication and expectation management with business units and management throughout the development stages.

Results:

• Built on an existing up-to-date daily data product with several million contracts
• Established an LLM setup coordinated with Data Protection and IT Security in the EU region, including data separation and approvals
• Defined three development stages through to partially autonomous management
• Designed role-specific views for business units, management and C-level
• Developed the business case and management pitch for the development stages
• Established an iterative response-quality validation process with the business unit
• Designed the operating model for assistance operations and initiated validation

Stack: Azure OpenAI, Azure AI Foundry, Snowflake, dbt, React, TypeScript, Entra ID, RAG, Agentic AI, analysis agents, Human-in-the-Loop, Prompt Engineering, LLM Evaluation, LLMOps, GDPR / EU region, Azure DevOps, Python, SQL, Change Management

• Owned requirements management for a connected mobile app integrating live vehicle hardware and embedded systems, from analysis through implementation (Requirements Management). App has grown to 500,000+ Google Play downloads and 5,800+ App Store ratings (4.4/5), ranking #170 in Germany's Navigation category.
• Steered digitalization and process optimization projects, coordinating between specialist departments, development teams, and external partners.
• Formulated requirements as user stories and acceptance criteria, accompanying implementation through testing and release.
• Applied genuine, practical AI Fluency to identify automation opportunities and accelerate delivery work. Applied SAFe and PRINCE2 methodologies; earned SAFe® 6 POPM and PRINCE2® Foundation certifications while in this role. Certified in Anthropic's AI Fluency framework.

GenAI – Chat & Voicebot

Setup of a GenAI solution with a knowledge base as well as chat and voicebots.

• Definition of use cases and chat/voicebot functionalities
• Project setup for cloud, knowledge base, LLMs and RAG
• AI guardrails, IAM concept
• Governance, Risk & Compliance (GRC)

Result:

Setup of an enterprise GenAI solution with knowledge base, chat/voicebots, IAM and governance.

• Built a private second brain: a local AI agent (Ollama) searches my documents using full-text and vector search (RAG).
• Connected it to the Claude app via MCP with its own OAuth server.
• Private content is filtered out in code before a request reaches Claude (privacy by design).
• Development is agentic: AI agents implement user stories, review agents check them, and I accept and merge them.
• Planned for release as open source.

Technologies: Ollama, RAG, vector search, MCP, OAuth, Claude, AI agents

• Built Azure Kubernetes clusters (AKS) with network policies, security groups, and RBAC
• Terraform-based infrastructure as code for secure, reproducible deployments in the BMW Azure cloud
• Hardened CI/CD pipelines with Jenkins, SonarQube, Fortify SSC, and Contrast AST
• Integrated SAP BTP/Kyma and ServiceNow GRC

• Project management and consulting services with a focus on IT interim management: digitalization of corporate management, including processes and applications
• Assessment of the entire IT infrastructure, including applications, core processes and contracts, including cost optimization
• Evaluation and implementation of solutions to promote digitalization in the company in the areas of property management, CRM, invoice review and approval processes, smart metering, DMS and time tracking
• Digitization of file folders and introduction of SharePoint and Microsoft Teams as central document and communication platforms
• Design and delivery of an AI workshop, including the rollout of AI tools to increase efficiency and transparency in key business processes
• Preparation of training materials and delivery of user training for newly introduced digital processes and solutions

• Analysis and optimization of the VMware environment for operation in a KRITIS environment
• Planning and implementation of updates to the VMware and hardware environment in a KRITIS environment
• Set up Skyline Health Diagnostics
• Review of the existing documentation
• Training and onboarding of new internal employees
• Support with migration and upgrade projects
• Preparations for moving scripts in the virtualization environment to GitLab
• Ticket processing with Service.Now

• Release Management
• Project Management
• Business Analysis
• Scrum
• SAFe

Designed and planned various data interfaces for "Big Data" processing of volleyball performance data, as Phase 1 of the major "Data Driven Content" project for the Volleyball Bundesliga, Berlin. UML modeling, interface design, monitoring implementation, commissioning, and user training. Negotiated a preliminary contract for Phase 2 in summer 2026.

Subproject Lead – Nearshoring Transformation

Project context: Support of a transformation program for relocating operational services to an international nearshore model

• Subproject lead
• Assessment of existing organizational and operating models
• Conducting GAP analyses
• Development of a sourcing readiness model
• Coordination of various departments
• Management of external partners
• Documentation of organizational changes
• Monitoring of the service provider / nearshoring partner

• Business and technical consulting for master data supply and process management
• Support with transition management
• Process optimization
• Interface definition

• Review and progress tracking of implementation requirements
• Ticket handling for major accounts
• Development of templates for product process descriptions