Text-to-Speech Experts in Germany

Built Python-based AI microservices and integrations for an AEC/VR Unity-based SaaS app, focusing on LLM/VLM capabilities, retrieval-backed systems, RESTful APIs, containerized deployment, and an automation microservice for the CAD-to-Unity pipeline.

• Developed a custom Hybrid A* based algorithm in C# to simulate hospital scenarios and detect early-stage design conflicts from collision/spatial data and generate structured reports.
• Solved and automated the time-consuming problem of converting CAD files to usable Unity environments with a custom-engineered and real-time pipeline using a ZeroMQ-based communication layer to distribute workloads across multiple processes and achieve real-time performance.
• Built a Dockerized FastAPI pipeline for CAD-to-Unity automation, combining vision-based object matching, image embeddings, and precomputed metadata to automatically map CAD objects to Unity behavior scripts, assign properties, and reduce repeated AI inference calls.
• Created documentation and examples to help technical users understand, configure, and extend the AI automation pipeline.

• Expert-supervised AI systems for scientific reasoning, model evaluation, and research workflows.
• Built the IAS Problem Solver, an orchestrated system for difficult mathematical reasoning; it achieved 84% in one submitted answer set on the Leipzig mathematics benchmark.
• Built a resumable state-machine pipeline for research-grade mathematics benchmark generation: source selection, LLM-agent-based phenomenon discovery, task synthesis, gold-answer and certificate generation and validation, probing, repair, human feedback, and quality gates, targeting tasks that are difficult, natural, verifiable, and cost-effective.
• Current work extends this into budget-aware AI research workflows for real scientific problems with expert review.

Tech stack: Python, OpenAI/OpenRouter-compatible APIs, embeddings, RAG, SQLite.

• Responsible for the concept, planning, and implementation of the product development of GetMyInvoices 2.0 and the subcomponent InvoiceRails
• Independent work on all aspects of the project, including concept, specification in tickets, and coordination of developers
• Creation, management, and prioritization of tickets to ensure all tasks are completed on time and with high quality
• Carrying out and/or coordinating tests and ensuring the proper implementation of the developed features and functionalities
• Close collaboration with developers to clarify technical requirements and ensure the implementations match the specifications
• Regular reporting on project progress and documentation of key decisions, changes, and risks
• Taking on the subject matter lead for all topics around e-invoicing and Peppol, especially in relation to the InvoiceRails component
• Internal consulting and knowledge sharing on e-invoicing and Peppol for other teams and departments
• Tracking market trends and new developments in e-invoicing and Peppol to continuously adapt the product strategy
• Ensuring the long-term scalability and flexibility of the products for future technical and regulatory changes in the e-invoicing area

• ▶ Built real-time voice assistant (STT → LLM → TTS pipeline) benchmarking and evaluating multiple STT providers including faster-whisper and Azure Speech. achieved sub-3s latency, Groq API (Llama 3) with multi-turn memory - directly handling edge cases in dictation, names and passcode recognition.

• Responsible for concept, camera, editing, animation, and grading for corporate and B2B productions
• Managing projects from budgeting to shoot and post-production through to delivery
• Since 2023, consistently using an AI-based production pipeline: Runway, Kling, Veo, Sora, and Seedance for stills and moving image
• ComfyUI for character consistency, ElevenLabs for voice, HeyGen for avatars
• Building reproducible workflows for scalable social formats
• Building local LLM infrastructure on my own GPU hardware: Ollama, multi-agent systems, RAG, speech-to-text, and text-to-speech
• Process automation for lead generation, email and API workflows, reporting, and document creation

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

Enterprise AI content categorization and AI-powered web research.

• Built multi-LLM evaluation framework with annotated data
• Iterated LLM error rates based on annotated datasets
• Implemented AI-powered web research pipeline Stack: LLM, evals, OpenRouter, Python, Node.js, TypeScript, React

• Industry: software manufacturer
• Tasks: project management; tracking and coordination of projects; stakeholder management; change management; prioritization of requirements; alignment of architecture; supplier management (internal and external); release management; monitoring defect resolution with the teams; AI-supported software development, software testing and code analysis; AI prompting, prompt engineering
• Software: Jira, Confluence, MS Project, MS Teams
• Environment: IT, software development, agile, artificial intelligence (AI)

• Development of an AI-supported personality analysis based on the institute's SDWA4: online survey, AI-supported and automated evaluation, and email delivery
• Requirements analysis, prototype development, evaluation, derivation of a simplified SDWA4-light analysis, continuous improvement, design, Make automation, deployment

End-to-end responsibility for all products - concept, architecture, development, and production operation as the sole developer; in addition, customer meetings, proposals, and marketing.

Underwriting Copilot - AI assistant for industrial insurance (in production at customer sites)

• Supports underwriters in analyzing industrial insurance submissions - in production use at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, mixed document sets.
• Two-stage evaluation and observability pipeline (code assertions + LLM-as-Judge) that makes answer quality, retrieval accuracy, and citation integrity measurable in a regression-safe way.

Kaiki Menu Analyzer - Data intelligence platform (in production at customer sites)

• Automatically captures and analyzes menu data from around 25,000 German restaurants.
• Scalable 7-container architecture (FastAPI, partitioned PostgreSQL, Redis/RQ) with LLM-supported extraction of structured data from PDF, HTML, and images.
• Full CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas - GEO platform (in production at customer sites)

• Measures brand visibility across five AI engines (ChatGPT, Gemini, Perplexity, Grok, Claude), each augmented with web search, orchestrated as a DAG workflow pipeline (Dispatcher → Sub-workflows → Scoring → Report) with fail isolation.
• 6-container deployment (FastAPI, Celery, Redis, PostgreSQL); LLM cost estimation, PDF audit report, rule-based cross-signal insights (no extra LLM cost).

Data Pipeline & Analytics Platform - competitive analysis in the automotive aftermarket

• Automated data pipeline with gap analysis algorithms and role-based access control; 230+ tests.
• Backend with FastAPI, PostgreSQL, SQLAlchemy.

Product development (actively in progress)

BankingGPT - AI assistant for complaint management in cooperative banking

• Security architecture at the core: no AI draft reaches the customer without human approval - the approval decision is in auditable code, not in the language model (monotonic: the model may escalate, never downgrade).
• Real agentic building blocks, each with its own boundary: the model chooses tools itself through an MCP server (read-only, allowlist, capped, fail-safe); sensitive cases are handed off via an open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented by me) to a separate specialist agent (securities/law), which never lowers the review requirement (pinned by test).
• Evaluation-driven over ten analysis rounds; uncovered a security flaw through independent review and blind tests that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered in the conversation, sensitive ones escalate before generation; response latency < 7 s measured (local GPU STT/TTS).

Stack & production readiness: Python, pydantic-ai, FastAPI/Celery, PostgreSQL/pgvector, FastMCP, fasta2a, Docker; multi-tenant capable (physical vector isolation per tenant), PII encrypted, OWASP-LLM reviewed, 275 tests, CI/CD; vendor-portable (Ollama / EU Cloud Vertex).

After-Sales Assistant - agentic RAG/GraphRAG assistant on public OEM manuals (automotive after-sales)

• Genuinely agentic on LangGraph: ReAct agent with four tools and conversation memory - the model decides on its own whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher - decodes warning lights), or a workshop/booking service.
• Human-in-the-Loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and gets the driver's explicit confirmation - the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as CI gate: a three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first when there is a critical warning?) blocks the pipeline; provider-agnostic (OpenAI/Azure/Anthropic), FastAPI with token streaming.

Stack: Python, LangChain/LangGraph, Chroma, Neo4j, RAGAS/DeepEval, FastAPI, Docker.

• Analysis
• Consulting
• Software design
• Development
• Automation
• Testing
• Deployment
• Architecture, development and deployment of various proof-of-concept applications around the integration of current AI interfaces including conversational, realtime voice, images and videos
• Developed best practices for working with agentic systems and AI in practice
• Created code templates

• Association member focused on supporting the sales structures of medium-sized businesses

• Clarification of project goals, scope, and functional target vision for building the AI-based knowledge base.
• Deriving the initial architecture and implementation strategy for the Zasterbot chatbot, including defining the MVP and expansion phases.
• Developing a functional target vision for building a structured knowledge base and integrating a future chatbot.
• Deriving and prioritizing use cases for information retrieval and provision by the chatbot.
• Modeling data structures and flows for effectively organizing the knowledge base on the Base44 platform.
• Designing and implementing data models for storing and linking relevant information.
• Developing processes for extracting, analyzing, and preparing raw data for the knowledge base.
• Ensuring data consistency and quality as the foundation for the future chatbot.
• Planning the integration of large language models (LLMs) and retrieval-augmented generation (RAG) for precise and context-aware responses.
• Implementing features for analyzing and visualizing data from the knowledge base.
• Using the Base44 platform with JSON-schema-based entities and a flexible permission model.
• Implementing Deno functions for backend logic, event processing, and external API integration.
• Integrating OpenAI services for initial data analysis.

• Microsoft Azure: design, sizing, and capacity analysis including PoC
• Microsoft Azure: final implementation for migration from on-prem RAC to single instance Data Guard
• Performance tuning and troubleshooting for crew management systems (pilots and briefings)
• Design and implementation of a disaster recovery-aware system based on RAC Extended Cluster and Data Guard
• OEM: Oracle Cloud Control maintenance, installation and upgrades (12.1.0.5 > 13.3 > 13.5)
• OEM: creating an agent golden image with new RU and security fixes for a full-scale environment
• OEM agent upgrade
• OEM: developing custom metric extensions and reports
• OEM: full monitoring setup with template collection and monitoring templates and incident rule configuration
• Upgrades: GI from 11.2.0.4 to 12.1.0.2, to 18.4, to 19.6+
• Upgrades: databases from 11.2.0.2 to 12.1.0.2, to 19.18+
• Redesign and license optimization based on Oracle SE on ODA and DBVisit
• Design of a virtualized platform based on OLVM and license optimization using hard partitioning
• Migration of databases from bare metal to OLVM