My Projects
Research projects, development work, AI experiments, design work and other creative endeavors.
All projects are built with modern technologies and best practices
personal
3D-Printed Water-Jet Propelled Surfboard
Designed and built a water-jet-propelled surfboard using primarily FDM 3D-printed parts (PLA). Integrated a waterproof electronics bay and a modular battery system; jet geometry was iterated in CAD for improved hydrodynamics.
Additive Manufacturing
Rapid Prototyping
Jet Drive
CAD Design
ai
Reinforcement Learning & Behavioural Cloning
Analyzed a real-world robotics demonstration dataset for connector insertion in cable assembly. Performed time-series preprocessing, value estimation (discounted returns), and visual analytics of human search strategies. Trained a Behavioural Cloning model (Keras) to imitate expert actions from state signals (pose, wrench, twist) for safer and faster policy initialization.
Pandas
TensorFlow
Robotic
Hyperparameter Tuning

ai
TUM.ai x Unite Hackathon
Built during the TUM.ai x Unite Hackathon, where our team achieved 1st place in Challenge 1 (Feature Normalization) and 1st place in Challenge 2 Level 1 (Core Demand Forecasting).
The project focused on solving real-world procurement and recommendation problems using machine learning. We developed systems for scaling and normalizing product features across millions of items and predicting core demand patterns to improve recommendation quality.
Python
Pandas
Machine Learning
Feature Engineering
Data Mining
AI-assisted Development

ai
Legacy AI
Legacy AI is an AI-powered knowledge preservation platform that captures, structures, and resurfaces institutional memory before it walks out the door. Built as a multi-tenant SaaS with role-based access, it combines conversational AI interviews, automated knowledge extraction, and semantic search to turn tacit expertise into a searchable, living knowledge base — so organizations never lose critical know-how when key people leave.
Next.js
ElevenLabs
pgvector
React
development
Development of a DLP-Printed Mullite Thruster with Tailored Porous Microstructures to Enhance Thermal Shock Resistance
This study explores the formulation of an optimized DLP resin enhanced with mullite particles for advanced satellite thruster applications. A systematic approach is employed to optimize printing and sintering parameters, assess porosity levels via the Archimedes principle, and characterize microstructural changes with scanning electron microscopy. Initial firing tests at pre-chamber combustion temperatures demonstrate the structural integrity of the printed components. Complementarily, the potential of tailored porous structures to further enhance thermal shock resistance is evaluated through specific microstructural design studies.
DLP Printing
High-Performance Ceramics
research
Aerospace Components
Developing propulsion systems and lightweight components for next-generation space and aircraft using advanced materials.
Aerospace
Engineering
Materials
Coming soon