System Online · Leipzig.DE

SEBASTIAN SIMON

PhD Student & Research Assistant

View Work Connect
// 01

ABOUT ME

Sebastian Simon

Hey! I'm Sebastian, a PhD student and research assistant at Leipzig University with a strong interest in the configuration landscape of modern software projects.

A key part of my research focuses on modeling and analyzing the configuration landscape of modern software systems to uncover the composition of their configuration space and how cross-technology configuration dependencies manifest. I also work with large language models (LLMs), retrieval-augmented generation (RAG), and agent-based systems to dveelop tools that help identify and validate configuration dependencies.

Outside of research, I enjoy staying active—CrossFit, bouldering, badminton, and going for runs are some of my favorite ways to unwind.

Technology Stack

Proficient in a range of programming languages and technologies including Python, Java, C#, Node.js, Spring, Maven, and Docker.

Artificial Intelligence

Hands-on experience with LLMs, embedding models, and advanced architectures such as RAG and agent-based systems.

Research

Extensive experience in empirical research, academic publishing, presenting, and applying research insights to practical software prototypes.

Project Organization

Skilled in supervising students and organizing courses such as software engineering internships and SE4AI.

// 02

PROFESSIONAL JOURNEY

Education/Work
2020 — Present
PhD Student / Research Assistant
Leipzig University

Modelling configuration landscapes of modern software systems and tackling configuration dependencies.

Software EngineeringAI/MLPython
Education
2018 — 2022
M.Sc. Computer Systems in Engineering
Otto-von-Guericke University Magdeburg

Thesis on finding test gaps in software systems using changed-based analysis.

Software EngineeringPython
Work
Apr 2019 — Sep 2020
Student Assistant
Selectline Software

Web application testing with Cypress.io and C# application development.

CypressJavaScriptC#
Work
Apr 2018 — Mar 2019
Student Assistant
SensoTech GmbH

Web application testing and automation using Selenium.

SeleniumC#
Internship
Sep 2017 — Dec 2017
Intern
Volkswagen AG

Web interface testing and test automation with HP UFT.

HP UFTVisual Basic
Education
2014 — 2018
B.Sc. Computer Systems in Engineering
Otto-von-Guericke University Magdeburg

Thesis on automated cross-browser testing.

JavaPythonAlgorithms
// 03

FEATURED PROJECTS

CfgNet

A framework for modeling the configuration landscape of software projects to detect and extract cross-stack configuration dependencies.

PythonPoetry
GitHub

RepoMiner

As part of my master thesis, I developed a tool to analyze the historical changes in software repositories to identify test gaps.

PythonFlaskPyDriller
GitHub

BoxOS

A platform for running a CrossFit Box and supporting athlete training.

FlutterClaude CodeCodexDockerDocker-Compose
GitHub
// 04

RESEARCH & PUBLICATIONS

PAPER

On Automating Configuration Dependency Validation via Retrieval-Augmented Generation

S. Simon, A. Mailach, J. Dorn, N. Siegmund

IEEE/ACM 40th International Conference on Automated Software Engineering, ASE 2025

We validated configuration dependencies via RAG, showing that incorporating tailored contextual information significantly improves the validation performance of all studied LLMs.

PDF
PAPER

Themes of Building LLM-Based Applications for Production: A Practitioner's View

A. Mailach, S. Simon, J. Dorn, N. Siegmund

IEEE/ACM 4th International Conference on AI Engineering–Software Engineering for AI (CAIN, 2025)

We mapped topics that practitioners discuss online about building LLM-based applications, offering practical insights into key considerations for developing such systems.

PDF
PAPER

A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation

S. Simon, A. Mailach, J. Dorn, N. Siegmund

ArXiv

This paper presents a methodology for a sound and reliable evaluation of RAG systems. We demonstrated its applicability on a real-world software engineering research task: the validation of configuration dependencies.

PDF Code
PAPER

Exploring Hyperparameter Usage and Tuning in Machine Learning Research

S. Simon, N. Kolyada, C. Akiki, M. Potthast, B. Stein, N. Siegmund

IEEE/ACM 2nd International Conference on AI Engineering–Software Engineering for AI (CAIN, 2023)

This work explores hyperparameter usage and tuning in machine learning research. We showed that most of the hyperparameters remain untouched, and those that have been changed use constant values. We also found a significant difference between tuning hyperparameters and the reporting about it in the corresponding research papers.

PDF Code
PAPER

CfgNet: A Framework for Tracking Equality-Based Configuration Dependencies Across a Software Project

S. Simon, N. Ruckel, N. Siegmund

IEEE Transactions on Software Engineering

We developed CfgNet, a framework that models the configuration landscape of a software project as a configuration network in an extensible and artifact-independent way. With CfgNet, we enable the early detection of possible dependency violations and proactively prevent misconfigurations during software development and maintenance.

PDF Code
// 05 · Open Channel

CONTACT ME

Let's connect — research collaboration, questions, or just to say hi.