Welcome to

Stefenos' Portfolio

I'm a server admin who builds things. Log services, small tools, automations, even site templates; as long as it runs on Linux, it's here!

View Projects
Our Logo

Tools

Everyday tools

Tools I'm using almost every day and have experience in

Python's brand icon

Python

Most of my projects are built in Python, my preferred programming language.

VSCodium's brand icon

VSCodium

All projects get built here, in the open source and telemetry-free distribution of VS Code.

DBeaver's brand icon

DBeaver

All database operations, whether it's about MariaDB, PostgreSQL or SQL Server, get done through this database management tool.

LibreOffice Calc's brand icon

LibreOffice Calc

Used to generate charts and apply mathematical formulas on sets of data when researching.

Docker's brand icon

Docker

Used to deploy projects or services quickly and efficiently such as databases, inventory systems and forums.

Debian's brand icon

Debian

Most of the servers and computer systems I manage run Debian or Debian-based distros like Linux Mint or MX Linux.

Research

Research areas

Topics I'm interesting in studying

Digital Ethics / Privacy

Studying system for responsible data use, algorithmic fairness and user privacy.

Archival

Preserving and Organizing Digital or Physical records to ensure accessibility and usability no matter the time.

Artificial Inteligence

Using Narrow (task-specific) AI to design systems that have a limited set of tasks focusing on improving day-to-day life.

Cybersecurity

Studying vulnerabilities, threat models, and defensive strategies to protect digital systems and data.

Projects

My projects

A selection of my most recent work

Publications

My latest publications

Recent research and writing from me

Thesis

Building a Learning Management System that integrates Large Language Models and Retrieval-Augmented Generation (RAG)

This thesis will address the asymmetry by covering the design and building of a prototype platform focused on both educators and students alike, providing students with accurate preparation material aggregated by their educators as well as providing said educators with automations that involve Large language Models (LLMs) to make course focused tasks easier to manage.

Forthcoming
30/08/2026, 09:00:00
Report

Implementing Large Language Models on Low-Power Embedded Systems

This paper presents a methodology for integrating LLMs into constrained environments, with a focus on the NVIDIA Jetson Orin Nano. We examine optimization techniques such as 4-bit quantization and knowledge distillation, which significantly reduce memory requirements with minimal accuracy loss.

Canceled
09/06/2026, 00:44:00

Get in touch

Contact me

Have a question, want to chat about a project, or feedback about something I wrote? Let me know!