Visual Studio Code Experts in Dortmund

• Complete greenfield rebuild across the whole stack — built AI-native: backend in Go and NestJS, PostgreSQL (CNPG) on K3s with GitOps/Terraform; frontend on Angular 22, zoneless.
• Orchestrated coding agents (e.g. Claude Code, Cursor) across the entire lifecycle — architecture, implementation, testing, reviews, documentation — driven by Specification-Driven Development (SDD).
• “Bruno” — LLM commentator persona backed by RAG and MCP for a personality that stays consistent across all generations (match previews, post-match reports, his own virtual bets).

Angular 22 (zoneless, without Zone.js), Claude Code, Claude Code Skills, CNPG, Cursor, Design Tokens (Spec for Code), Docker, Gherkin, Git, GitLab, GitOps, Go, Google Gemini, Grafana, Hetzner Cloud, K3s, Keycloak, Kubernetes, Lighthouse, LLM Integration, Model Context Protocol (MCP), NestJS, Node.js, NPM, Playwright, PostgreSQL, Prometheus, RAG, REST, Specification-Driven Development (SDD), Structured Outputs, Terraform, TypeScript, Vitest

Conventional Paradigm Test (CPT) – AI Evaluation & LLM Research

Development of an experimental evaluation approach to examine “paradigmatic closure” in Large Language Models — that is, the question of how far LLMs can recognize the basic assumptions, values, and limits of the paradigms within which they generate answers.

Design and testing of an additional approach to classic AI benchmarks that does not primarily measure factual correctness or task performance, but instead examines a model’s ability to recognize alternative perspectives, make implicit assumptions visible, and reflect on the limits of its own answer or interpretation framework.

Focus areas: development of evaluation criteria and test questions · LLM evaluation and comparative model analysis · prompt and response analysis · qualitative classification of model answers · study of epistemic compression and value leakage · benchmark and literature research · development of structured assessment and analysis methods

As part of CPT, existing AI evaluation approaches and benchmarks were analyzed, and a minimalist test protocol was developed that classifies model answers by response patterns such as DIRECT, CLARIFY, PLURALIST, REFUSE, and META-AWARE. TruthfulQA was used as the basis for experimental application and comparison with existing reference answers.

Technologies & Methods: Large Language Models (LLMs) · Generative AI · Prompt Engineering · AI Evaluation · TruthfulQA · Benchmark Analysis · Human-in-the-Loop Evaluation · Qualitative Content Analysis · Research & Literature Review

• Optimization of the transmission media of the data links in the Ruhr area
• Configuration/expansion of switches and routers for an autonomous system AS
• Improve the network protocols used Layer 2/3 (OSI model), RSTP, broadcast, etc.
• Laying cables, crimping, antennas, routers, switches
• Maintenance, expansion, selection and prioritization of troubleshooting measures for network monitoring (PRTG, The Dude)
• Organization and new connection of another BGP peering, data center, NGN fiber optic
• VPN IPSec site connections for 6 sites with PFSense, Fritzbox
• Configuration of WLAN devices (Mikrotik, UBNT

Label: TCP/IP, VLAN, BGP, OSPF, MPLS, VPLS, routing protocols, WLAN, EoIP, PPPoE, routing, SNMP, DHCP, DNS, NAT, native IP, VLAN, Ethernet, VoIP., switches and routers from: Nortel, Cisco, MikroTik, UBNT., network management systems: The Dude, PRTG, UISP

• Development and enhancement of scalable Vue.js/TypeScript applications, as well as reusable components and frontend architectures
• Development of modern, high-performance web applications for internal software solutions using Vue.js, Pinia, and Vuex
• Efficient integration and processing of data from external APIs to support frontend development and ensure smooth end-to-end functionality
• Implementation and maintenance of automated tests for quality assurance using Vitest
• Creation of interactive website prototypes in Figma and Adobe XD as a basis for Vue.js implementations
• Participation in technical reviews and code reviews to ensure high code quality and continuously improve development processes
• Use of AI-supported development tools such as ChatGPT and Claude for more efficient development, error analysis, and code optimization
• Use of CI/CD pipelines for the efficient integration of automated tests, builds, and deployments into the development workflow

• Technical lead of a team developing agentic chatbot solutions (React, TypeScript, Python, FastAPI)
• Architecture design for multi-LLM dialog systems - focus on maintainability, UX, and autonomous execution
• Stakeholder alignment, CI/CD processes, and AI integration at enterprise level

• Further development and release support for a white-label ePA component for health insurance companies
• Technologies: Android (Kotlin), Kotlin Multiplatform, Coroutines, Jetpack Compose, MVVM, StateFlow, Gradle, ProGuard

• New development of a web app to manage and configure counting devices for large events
• Technologies: .NET 10, C#, Blazor, MudBlazor, MySQL, Git

• Teaching JavaScript, HTML, CSS, React, NodeJS, MongoDB, MariaDB, and Express
• Designing and preparing lessons
• Classroom teaching and one-on-one coaching

• Implementation of various interfaces for subsystems and connection to external devices (cameras, scanners, digital lockers)
• Development of various interfaces in the used cars area
• Realization of various prototypes
• Support in UI/UX and data analytics
• Development of frontend and backend solutions
• Kubernetes migration
• Building CI/CD pipelines
• Communication with the business unit and technical design of new solutions
• Cross-team alignment and coordination within the team
• Overview of the entire technology stack and related systems
• Documentation, preparation, and conducting of reviews
• Supporting the team and coordinating releases and key milestones