Robin Morgenstern.
I build dependable software across AI, automation, mobile, and distributed systems.
M.Sc. Computer Science student at TU Dresden. Working Student at Infineon & developer of HideZone.
About
I am a Computer Science Master's student at TU Dresden. Alongside my studies, I work as an Automation & AI working student at Infineon (Siltectra), as a student assistant at the university, and as an independent software developer.
At Infineon, I build internal applications and automate operational workflows, including an AI-assisted Jira ticket pipeline and improvements to a maintenance chatbot. At TU Dresden, my work spans computer vision, edge systems, knowledge graphs, and LLM evaluation for industrial maintenance.
As an independent developer, I build and run complete products. HideZone, my real-time GPS multiplayer game, has reached more than 40,000 downloads across Google Play and the App Store. I have also delivered remote desktop and virtual-machine support tools for enterprise clients.
I work mainly with Python, Docker, Flutter, and TypeScript. I prefer clear system boundaries, useful tests, and software that remains dependable after it ships.
Experience
Working Student, Automation & AI
Infineon Technologies AG (via Siltectra GmbH)- Develop and maintain internal applications that support semiconductor manufacturing workflows.
- Extend an internal maintenance chatbot with workflow automation and enterprise authentication, including Single Sign-On.
- Built an AI-assisted workflow that turns meeting recordings into structured Jira tickets.
Independent Software Developer
Self-Employed- Built and now operate HideZone, a real-time GPS multiplayer game with more than 40,000 organic downloads across Google Play and the App Store.
- Delivered a remote desktop client with time-bound authentication for an enterprise customer.
- Built a mail-routing service that forwards incoming messages to users on dynamically assigned virtual machines.
Student Assistant
TU Dresden- Developed a distributed maintenance-assistant prototype with SSD object detection, Dockerized Flask services, and Raspberry Pi edge hardware.
- Implemented camera calibration, image-quality checks, local server discovery, and projector-based guidance for industrial machinery.
- Built a pipeline that converts single- and multi-camera object detections into OWL knowledge graphs with derived spatial relations.
- Currently developing an LLM-based ontology generation and benchmarking suite with hierarchical merging, automated quality evaluation, and a Next.js control interface.
Skills
The tools and technologies I reach for most.
Languages
ML & AI
Frameworks
Infrastructure
Projects
Selected work across machine learning, mobile, and systems engineering.
Solo build · 40,000+ downloads · 2025 - present
HideZone: IRL GPS Hide & Seek
A real-time outdoor multiplayer game for iOS and Android, with live GPS, custom play zones, tactical items, and seven game modes. 40,000+ downloads.
Research paper · TU Dresden · 2026 - present
LLM-Based Ontology Generation
An experimental framework that turns long-form text into structured ontologies, merges them hierarchically, and benchmarks their semantic and structural quality.
Research project · TU Dresden · 2024 - 2025
AI Maintenance Assistant
A projection-based maintenance prototype that detects machine components on a server and maps visual guidance back onto the physical workspace.
B.Sc. thesis · Graded 1.4 · 2025
Bachelor Thesis: Spatial Knowledge Graphs
Generating OWL knowledge graphs from object-detection output and evaluating how graph structure, format, and model size affect spatial question answering. Graded 1.4.
More projects
Coursework, research, and this site itself.
Research project · +16 pp SAQ accuracy · 2025 - 2026
SecretLLM: Cultural QA System
A quantized Llama-3-8B cultural QA pipeline using LoRA fine-tuning and dynamic few-shot retrieval, improving short-answer accuracy by 16 percentage points.
Solo build · Nov 2025 - Jan 2026
Portfolio Website
This site: a statically generated Next.js portfolio with typed content, case-study pages, flash-free theming, and live GitHub activity.
University team project · 8 people · 2023 - 2024
Software Technology Internship
A browser-based beverage, inventory, and billing system built with Spring Boot by an eight-person Scrum team.
University course project · 2023
Autonomous Maze Navigator
A LEGO EV3 rover that follows lines, detects obstacles, maps an unknown planet, and coordinates routes with a central server.
Let's talk.
Have a role, a project, or just a technical question? My inbox is open.
Get in touchmorgensternrobin04@gmail.comDresden, Germany