Automatic Speech Recognition Experts in Germany

Project: Design and implementation of an AI product for four business use cases

Project management for an AI project at a leading provider of large-scale catering and food services, where a production-ready AI product for four use cases was implemented together with an external development partner: automated briefings based on CRM and document data, voice-based capture and structuring of reports, detection and consolidation of duplicates in master data, and data-based market analyses. A key focus was a data-protection-compliant architecture that passed the internal IT security review and enabled production use.

• Translation of business requirements into clearly defined AI use cases with a focused product scope and clear value proposition
• Selection and evaluation of models and architecture options for text extraction, speech-to-text, and context enrichment from business systems, including LLM integration, function calling, and retrieval
• Development and implementation of an architecture with European hosting, data minimization, and masking of personal data as a prerequisite for approval
• Management of interfaces between business departments, IT, IT security, and the external development partner under restrictive data access conditions
• Coordination with the CIO and executive management levels on data access, risk assessment, and approval decisions
• Preparation for the transition to production use

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.

• 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 pricing through shooting and post-production to delivery
• Since 2023, a continuous AI-supported production pipeline: Runway, Kling, Veo, Sora, and Seedance for image and moving image content
• ComfyUI for character consistency, ElevenLabs for voice, HeyGen for avatars
• Building reproducible workflows for scalable social media 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

• Lead a team of 15 annotators on large-scale computer vision projects for autonomous vehicle systems
• Developed comprehensive annotation guidelines that improved inter-annotator agreement by 35 percent
• Implemented quality control processes that reduced error rates by 42% across all projects
• Collaborated with ML engineers to identify edge cases and improve dataset quality
• Managed annotation projects for Fortune 500 clients, delivering 100% on time

• Managing projects on site
• Coordinating various stakeholders (Operations, IT, Maintenance, suppliers, service providers)
• Leading technicians and external contractors
• Planning resources, schedules, and budgets
• Quality, risk, and safety management
• Conducting daily status meetings
• Escalation management and problem-solving
• Maintaining project tracking, ticket systems, and KPI dashboards
• Materials and spare parts management
• Preparing reports and project status updates

Environment: Infrastructure, Logistics

• Teaching German literature and linguistics

• Built a Trend-Scouting AI system to automate technology intelligence in power electronics and semiconductors, combining Azure OpenAI with LangChain, Scrapy-based web crawling for structured, noise-free data acquisition, and automated PDF reporting for internal R&D use. Developed a FastAPI-based (Uvicorn) web application to validate LLM outputs, test prompt strategies, and enable interactive system evaluation.
• Developed a real-time STM32 binary telemetry debugger with a PyQt-based GUI, featuring header-based frame synchronization, anomaly detection, template-driven payload decoding, time-aligned buffering, and live signal visualization.
• Developed an AI-driven power inductor designer using surrogate regression models for accurate electromagnetic and thermal prediction. Integrated multi-objective NSGA-II optimization to generate efficient, manufacturable designs.

• 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.

• Development and rollout of a browser-based platform for camera streaming, augmented reality (AR), and visual computing
• Device-independent camera streaming for smartphones, tablets, desktop PCs, as well as VR and AR headsets
• Ensuring GDPR-compliant hosting in Open Telekom Cloud and other sovereign cloud providers
• Intuitive visual and collaborative features to increase efficiency and integrate smoothly into existing business software

• Research and develop models for chatbots, NLP and LLMs (e.g. Llama, Qwen, OpenAI)
• Enhance chatbots with RAG, in-context learning
• Supervised fine-tuning (PEFT, LoRA), Huggingface or Unsloth
• Advanced training methods: Test-time training, (transductive) active learning, reinforcement learning
• High-throughput serving with vLLM
• Apply embedding models (e.g. SentenceTransformers), similarity/vector search or vector DB or ranking (e.g. LlamaIndex, Faiss, LangChain)
• Generate and filter synthetic data, clustering
• Detect hallucinations
• Evaluate chatbot models (Rouge, BLEU, F1-Score, Recall, Precision)
• Visualization of experiments (matplotlib)

• Introducing 5 different process applications for various teams

• Release planning: scope and time management

• Resource/capacity planning

• Conducting sprint planning / retrospectives

• Increment planning (multiple sprints)

• Preparing steering committee meetings / reporting to the executive board

• Coordinating / aligning with external suppliers / deliveries

• Multi-project resource planning

• Aligning with the business unit and development team

• Identifying best practices with IBM BAW

• Cost control and planning for the project team and external service providers

• Collecting KPIs using LogScale

• Analyzing application errors with LogScale / queries

• Defining user stories / aligning requirements with the business unit and development team

• Testing and defect tracking

• UI/UX design of the application

• Preparing and facilitating brown-paper workshop

• Test concept, test data, test organization, test execution

• Recording team velocity / metrics

• Executing tests

• Scripts for automated testing

• Organizing tests with the business unit and IT

• Recording and prioritizing defects

• Setting up and operating the application

• Setting up application monitoring with LogScale dashboards

• Checking health endpoints with PowerShell

• Post mortem analysis

• Setting up incident management

• Setting up problem management

• Analyzing errors using LogScale queries and dashboard

• Pre-processing data for AI

• Conducting evaluation with AI language models (Meta Llama 3.3 LLM and deepset Haystack) and RAG

• Installing runtime environments for LLMs (large language model)

• Evaluating various LLMs

• Installing RAG (retrieval augmented generation) and integrating with LLM

• Extracting unstructured data with LLM and RAG

• Project based on IBM BAW (Business Automation Workflow), WebSphere Liberty, Domea, d.3, REST, LogScale (formerly Humio), Swagger, PowerShell, JIRA, Confluence, Lucom Interaction Platform (LIP), Mattermost, Jabber