Selected engineering work · Munich, Germany

Engineering portfolio

Project index

Solar-car driving strategyLarge-scale optimization
Confidence calibration of 3D LiDAR object detectorsMachine-learning research
TUfast autonomous stackAutonomous systems
TUfast matching toolCombinatorial optimization
End-to-end LTE/4G vehicle telemetryEmbedded infrastructure
Self-learning dough-strand controllerIndustrial AI

01 · Large-scale optimization

Solar-car driving strategy

Head of Driving Strategy, TUfast e.V. · May 2024–present

A solver-agnostic system that calculates how a solar car should use limited energy during the Bridgestone World Solar Challenge.

Optimization: Developed an AI-based race simulation with one-second accuracy and solved a constrained nonlinear problem with 200,000 parameters.
Compute: Used PyTorch, Adam-style optimization, CUDA Graphs, TensorBoard, Docker, CI/CD, and NVIDIA H100 GPUs.
Operations: Led strategy simulation and supported remote race telemetry with PostgreSQL, Grafana, VPN/Tailscale, and Starlink.

Technologies

PyTorch
CUDA
Adam2
Docker
PostgreSQL
Grafana

White TUfast solar car with solar panels beside a World Solar Challenge banner. — The solar car whose race energy use the strategy system optimizes. · Full size

Optimizer output plots showing velocity, slope, battery, distance, solar power, acceleration, and speed limits. — Technical output across velocity, battery, solar power, and race constraints. · Full size

Back to projects

02 · Machine-learning research

Confidence calibration of 3D LiDAR object detectors

Master’s thesis, TUM / MIRMI · June 2024–January 2025 · Grade 1.7

Research into whether a 3D detector’s confidence scores reliably represent the probability that its predictions are correct.

Result: Reduced miscalibration by 12.8 percentage points, from 15.9% to 3.1%, using custom loss functions and calibration tooling.
Research: Trained and evaluated 3D LiDAR detectors on the Waymo dataset using NVIDIA H100 cluster resources.
Publication: The resulting paper was accepted at the 2025 IEEE Intelligent Vehicles Symposium.

Technologies

Python
PyTorch
Waymo dataset
Slurm
Docker
NVIDIA H100

Read the IEEE paper

Back to projects

03 · Autonomous systems

TUfast autonomous stack

Autonomous development, TUfast e.V. · May 2022–May 2024

Perception and sensor integration for a Level 4 competition vehicle in the Shell Eco-marathon Autonomous Urban Concept category.

Perception: Built 3D localization, map-less driving, OctoMap mapping, camera/LiDAR fusion, and road and parking-spot detection.
Integration: Developed a custom Sekonix camera driver, merged camera and LiDAR point clouds, used Coral TPU acceleration, and prepared NVIDIA DRIVE.
Leadership: Led the autonomous team from May 2023; trained detectors on a self-developed dataset using LRZ AI Cluster resources.

Technologies

ROS2
Python
C++
PyTorch
TensorFlow
OctoMap
Coral TPU

Watch the vehicle video

Vehicle hardware rendering showing wheels, sensors, electronic modules, and their wiring. — The system layout connects vehicle hardware, sensors, and compute components. · Full size

Back to projects

04 · Combinatorial optimization

TUfast matching tool

TUfast engineering software · Public repository

A desktop planning tool that turns constrained shift assignment into a graph-optimization problem.

Problem: Assign shift leads and workers while respecting planning constraints.
Approach: Modeled constraints with maximum-flow and min-cost-flow algorithms using NetworkX and SciPy sparse graphs.
Delivery: Implemented and tested the matching behavior, then packaged it as a PySide6 GUI application.

Technologies

Python
NetworkX
SciPy
PySide6
Max flow
Min-cost flow

View source on GitHub

TUfast matching-tool interface with spreadsheet inputs, shift constraints, and shift-plan generation controls. — The delivered desktop application collects planning inputs and generates a constrained shift plan. · Full size

Back to projects

05 · Embedded infrastructure

End-to-end LTE/4G vehicle telemetry

TUM School of Computation, Information and Technology · October 2023–May 2024

Reliable, energy-efficient telemetry connecting the muc023+ competition vehicle to remote engineering tools.

Edge: Collected vehicle data with Linux, Raspberry Pi, CAN bus, C/C++, and Python.
Transport: Connected the vehicle over LTE/4G using VPN and Tailscale.
Backend: Used PostgreSQL database replication and a Grafana web interface for remote monitoring.

Technologies

Linux
Raspberry Pi
CAN bus
LTE/4G
C/C++
PostgreSQL
Grafana

Back to projects

06 · Industrial AI

Self-learning dough-strand controller

Bachelor’s thesis with Lieken GmbH · June–August 2021

A self-learning controller that keeps bread weight constant as dough consistency changes on an automated production line.

Control: Designed and optimized the controller around two key variables in the automated dough-flow process.
Delivery: Implemented the self-learning controller in Python for an industrial production setting.

Technologies

Python
PLC
ODBC
pytest
PyPI
GitHub Actions

Back to projects