Prompt Engineering Experts in Dortmund

• Setup of new desktop computers
• Setup of a VPS for automation, databases, and chat interface
• Connection to Azure AI Foundry
• Development of various n8n workflows for email, social media, and document management
• Implementation of a QM system (backups, error handling, HITL)
• Setup and optimization of an inbound Voice Agent

Designing AI-native digital products by combining product strategy, UX research, interaction design, software engineering, and modern AI workflows. Leading projects from discovery to implementation while integrating AI throughout the entire product development lifecycle.

Key responsibilities

• → Product discovery, stakeholder workshops, Jobs-to-be-Done and user research
• → User journey mapping, information architecture and interaction design
• → Wireframes, high-fidelity UI, prototypes and scalable design systems in Figma and Penpot
• → AI-assisted interface generation and rapid concept exploration using Figma AI, Figma Make and generative design workflows
• → Design-to-code workflows with AI-supported frontend generation and engineering collaboration
• → Building accessible interfaces following WCAG 2.2 and enterprise design standards
• → Usability testing, iterative validation and KPI-driven product optimization
• → Development of AI knowledge systems, MCP-powered design workflows and human-in-the-loop review processes
• → Close collaboration with engineering teams to ensure production-ready implementation

• 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

• Technical design, prioritization, and hands-on implementation of AI automation, conversational AI, voice AI, and private AI solutions.
• Translation of business requirements into system architecture, conversation/workflow logic, APIs, data flows, and production-ready AI workflows.
• Development of backend and integration components with Python/FastAPI, PostgreSQL/pgvector, Redis, REST APIs, webhooks, and background jobs.
• Design and implementation of RAG architectures with local/private LLMs, embeddings, document processing, semantic search, and controlled access to company knowledge.
• Prompt engineering for LLM and voice/conversational AI applications; iterative optimization based on real processes, system responses, and quality requirements.
• Practical work with ElevenLabs and its APIs in a voice AI project, as well as technical evaluation and integration of voice AI components.
• Deployment and operation of Docker-based systems on Linux with Nginx, CI/CD, monitoring/logging, backup/restore, and reproducible deployment processes.

• Developed and optimised structured support workflows and evaluation procedures, applying consistent quality standards across high-volume operational tasks.
• Monitored performance metrics to identify systemic issues and drive targeted improvements — a skill directly transferable to LLM performance metric analysis.
• Managed escalations and maintained high accuracy and satisfaction standards in a fully asynchronous, remote-first environment.

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

• Development of an automated job-scouting workflow for the aggregation and LLM-based evaluation of job postings from RSS feeds and APIs.
• Development of a Telegram bot for voice and text messages, featuring LLM-supported processing, summarization, and structured JSON output.
• Implementation of a personal task-planning assistant using n8n, OpenRouter, and Supabase for automated daily and knowledge organization.
• Development of LLM chatbots for structured knowledge retrieval utilizing prompt constraints, guardrails, and forced output formats.

• Led the 12-week training program to become an AI and automation specialist
• Created training materials & video courses on "AI Fundamentals", "Working with ChatGPT", "Prompt Engineering", "AI Agents with N8N", "Automations with Make.com" & AI-generated marketing content (images, videos, blog posts & social media posts)
• Conducted workshops on the above topics
• Tools: Loom, N8N, Make.com, ChatGPT, Midjourney, Gamma.app, Canva, Kling AI, Magnific AI
• Result: Participants learn the technical and business know-how to successfully build a business as AI and automation specialists

• Conduct structured evaluation of LLM outputs using Content Review Standards (CRS) and AI safety frameworks.
• Assess responses across high-risk domains including violence and criminal facilitation.
• Assess responses across high-risk domains including hate speech and harassment.
• Assess responses across high-risk domains including suicide and self-harm.
• Assess responses across high-risk domains including regulated advice (medical, legal, financial).
• Assess responses across high-risk domains including misinformation and fabricated claims.
• Assess responses across high-risk domains including defamation and intellectual property.
• Assess responses across high-risk domains including child safety and sexual exploitation.
• Assess responses across high-risk domains including political and sensitive content.
• Apply youth-protection and age-appropriateness guidelines to prevent unsafe facilitation or restricted substance guidance.
• Classify prompts as adversarial, borderline, or benign based on contextual intent and risk analysis.
• Evaluate model behavior types including correct refusal, partial refusal, over-refusal, under-refusal, improper compliance, and ignorance-based outputs.
• Identify policy misapplications and user-intent misinterpretation patterns.
• Designed structured adversarial and borderline multi-turn conversation flows to stress-test AI boundary enforcement and reasoning stability.
• Identified failure modes including hallucination, unsafe compliance, excessive refusal, contextual drift, and inconsistent safety logic.
• Applied a structured four-dimension evaluation rubric covering accuracy & safety, relevance & completeness, clarity & structure, and tone & appropriateness.
• Provided structured feedback supporting supervised fine-tuning and reinforcement learning from human feedback processes.
• Rewrote unsafe or misaligned outputs into compliant, accurate, and helpful responses.
• Performed Persian ↔ English translation and translation validation of AI-generated content.
• Assessed semantic accuracy, contextual consistency, and safety alignment across languages.
• Identified mistranslations, cultural nuance issues, and cross-lingual policy inconsistencies.
• Recognized with the Above & Beyond Award – Q3 2025 for exceeding quality standards and embracing innovation.