1) AI Automation & Enterprise Delivery

• OfferGenerator (Flask → PowerPoint): implemented, tested, and deployed on a Domain Network; Manual offer creation was reduced from 4–5 hours to ~30 minutes (≈85–90%). More information. See demo.
• Tender/Ausschreibung Generator (Flask → PowerPoint): designed for structured Generation of BA/MSc announcements; PDF Extraction, Template-driven PPTX Generation, and Azure/OpenAI-based Text Generation are integrated. Source content is derived from official PEM study pages (see: pem.rwth-aachen.de/go/id/fecr ). Automated export to Network Locations is supported. More information. See demo.
• PowerPoint Add-in (C#, .NET Framework VSTO/COM): implemented, tested, and deployed on a Domain Network and developed as an internal Productivity Tool; GPT-enabled Text and Image Generation, Image Analysis, and different Text-to-Diagrams/Charts are provided; Production deployment for staff use has been established. More information. See demo.

2) Enterprise AI (Privacy-First)

• On-Prem RAG (offline / privacy-first): Retrieval-Augmented Generation for internal Knowledge Workflows; Emphasis is placed on Governance, Operational Robustness, and Deployment constraints in Enterprise Environments. More information. See demo.

3) Speech & Emotion Recognition (ASR/SER)

• AI-based Development: Speech & Emotion Recognition — Two Models: Separate Models for Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER) have been trained via wav2vec2 fine-tuning; Both audiofile-based and real-time inference are supported; Evaluation is performed via Word Error Rate (WER) and Unweighted Average Recall (UAR).
• HPC Training (RWTH High Performance Computing): Training and Inference workflows of the ASR/SER models are executed on RWTH HPC (SLURM) to accommodate large-scale datasets and controlled experiments. More information. See demo.

4) Enterprise IT & System Integration (Avantis + BIC)

• Identity & Access: Active Directory and Group Policy Objects (GPO) are administered, including Groups/Permissions, Service Accounts, and File Server Access Control.
• Stability & Security: WSUS patching, Sophos Endpoint Security, CommVault Backups, Standardized Rollouts, Documentation, and Security Awareness/Testing are applied to support stable Operations.
• Site Operations: Multi-site Infrastructure work has been delivered at PEM Avantis and the Battery Innovation Cluster (BIC) .

5) XR Learning Technologies (RWTH LearnTech)

• Project Context (04/2022–10/2023): contributions were delivered within the RWTH LearnTech environment (see LearnTech), including the Unity-based xTeach VR project (see xTeach VR).
• Spatial Audio Integration: Google Resonance Audio was integrated and parameterized for improved Realism of Distance and Room Perception in immersive Learning Environments (Unity-based audio Pipeline Design and Tuning).
• Learning Analytics Instrumentation: keyword recognition and interaction events were operationalized via xAPI; Statements were collected in a Learning Record Store (LRS) for subsequent Analysis.
• Analytics Visualization: Learning Analytics were processed and visualized through a React-based dashboard, enabling structured exploration of user behavior and interaction patterns.
• Research Stimuli: Experimental Stimuli were created and iteratively optimized to support controlled Studies (Audio Stimulus Engineering and Quality Assurance under Research Constraints).
• Publication: Teaching and research context—including this project period—is documented in the Osnabrück Teach-R publications (PDF).

6) Web Design & Web Development

• Front-End — UX/UI & Presentation Layer: Layout, typography, spacing, responsive behavior, and information architecture are treated as first-class design and engineering concerns. The implementation of semantic HTML, modular CSS, and JavaScript-based interaction patterns enables maintainable templates, accessible landmarks and labels, mobile-friendly presentation, and consistent user flows across desktop and mobile surfaces. Pragmatic asset choices — including vector icons, optimized font loading, restrained third-party dependencies, and performance-aware component integration — support fast rendering, visual stability, and production-ready user experiences. Visit site 1, Visit site 2
• Back-End & Server-Side Delivery: Application logic, routing, validation, form workflows, secured endpoints, and API-backed integrations are implemented as part of reliable server-side delivery. SQL-based database structures support schema design, persistence, operational queries, and AI-ready data workflows. This backend foundation extends into on-premises RAG architectures, where documents are processed, stored, embedded, vectorized, and retrieved through structured database-backed pipelines. Server provisioning, runtime configuration, and environment hardening support stable deployment across hosted and on-prem infrastructure, aligned with the engineering discipline used for internal Flask-based tools, customer-facing platforms, and portfolio-facing web properties. See project.

Audio Engineering (Mixing & Mastering)

Professional mixing, mastering, and audio production are supported by experience in custom audio processing and spatial audio for interactive applications, cinematic or gaming projects. More information.

Video / Audiovisual

Audiovisual production, sound design, and experimental stimulus design have been delivered for research-driven and narrative contexts. More information.