Open to remote & onsite opportunities

Building AI applications that solve real problems

I'm an AI & Machine Learning Engineer with a background in backend software engineering, specializing in LLM systems, autonomous agents, RAG pipelines, and scalable Python applications. Currently pursuing an M.Sc. in Artificial Intelligence Engineering at JKU Linz while turning complex AI ideas into reliable, production-ready software.

agent.py
python agent.py --mode rag
Initializing LangGraph ReAct agent...
Loading vector store ChromaDB
Embedding model "llama3" loaded ✓
 
Agent: Analyzing your query...
→ Retrieved 5 relevant chunks
→ Self-correcting code execution...
→ Generating structured report
 
98.4%
mAP50 — ALPR System
3.5ms
Inference time on NVIDIA T4
95.6%
Accuracy — Traffic Sign Recognition
5+
AI systems built
3+
Years with Python development
M.Sc.
AI Engineering · JKU Linz
Expertise

Technical Skills

LLM & Agents
LangChain LangGraph RAG Systems HuggingFace ReAct Agents Vector Search
Computer Vision & ML
PyTorch OpenCV YOLOv8 Scikit-learn Deep Learning MARL
Backend Engineering
Python FastAPI Django Flask REST APIs Streamlit
Cloud & Infrastructure
AWS EC2 AWS S3 AWS IAM Docker Linux Git
Databases
PostgreSQL MySQL MongoDB ChromaDB Oracle SQLite
Languages
Python C# C/C++ Java MATLAB
Overview

Professional highlights

Dynatrace
Python Monitoring Extensions Cloud Observability Distributed Systems
Backend Engineering
FastAPI Django REST APIs Databases
Artificial Intelligence
LLM Systems RAG Autonomous Agents Computer Vision
Industrial Software
Automation Systems Oracle PL/SQL C#
Work

Selected projects

01
DataPilot AI
Autonomous Data Analysis Agent

The problem with most data analysis tools is that you need to know what questions to ask. DataPilot takes a different approach, given a CSV file, the agent plans its own analysis steps, writes Python code to execute them, retries on failure, and produces a structured PDF report with charts. The interesting engineering challenge was building a reliable code execution loop with self-correction, so the agent recovers from runtime errors without human intervention.

CSV Upload Planning Agent Code Execution Self-Healing PDF Report
Autonomous planning Self-healing execution Live agent reasoning PDF generation
LangGraph Pandas Streamlit ReportLab Matplotlib
02
RAG Knowledge Base Chatbot
Document Retrieval with Citation Grounding

Built a RAG application that lets users query their own documents and receive answers grounded in the source material, with citations pointing back to specific passages. The pipeline covers document ingestion, chunking, embedding, vector storage, retrieval, and response generation. Packaged with a FastAPI backend and Streamlit frontend, deployed via Docker. The main challenge was keeping responses grounded in the uploaded documents while maintaining low retrieval latency. The pipeline combines document chunking, vector search, and citation generation so users can trace every answer back to its source.

PDF Ingestion Embedding Vector Search LLM Generation Cited Answer
Citation grounding Dockerized deployment FastAPI backend Full pipeline
LangChain Llama3 FastAPI Docker ChromaDB
03
ALPR System
Real-Time License Plate Detection

Trained and optimized a YOLOv8 model for real-time license plate detection, with the goal of making it fast enough for live camera input. The focus was on the inference pipeline, getting latency down to ~3.5ms on NVIDIA T4 while keeping accuracy high. Evaluated using mAP50 and F1-score, achieving 98.4% and 96.6% respectively.

Camera Feed YOLOv8 Detection OCR Structured Output
98.4% mAP50 96.6% F1-score ~3.5ms inference NVIDIA T4
YOLOv8 PyTorch OpenCV Python
04
Cooperative Warehouse Agents
Multi-Agent Reinforcement Learning

Built a MARL environment where multiple agents must coordinate to solve warehouse tasks without being able to observe the full state. The core question was how agents develop cooperation strategies without explicit communication. Studied the effect of different reward shaping approaches on coordination quality and training stability across several algorithms, and analyzed where independent learning breaks down at scale.

Environment Partial Obs. MARL Training Coordination
Cooperative MARL Partial observability Reward shaping
PettingZoo PyTorch NumPy Matplotlib
Background

Experience

Jul – Sep 2025
Dynatrace · Linz, Austria
Software Engineer Intern
Built a Python monitoring extension that pulls real-time air quality data from the Open-Meteo API and feeds it into Dynatrace's observability platform
Customized monitoring dashboards to improve how environmental data is reported and visualized
Worked within distributed cloud infrastructure and gained exposure to how large-scale observability systems are structured
Python REST APIs Cloud Monitoring Distributed Systems Observability
Jun 2024 – Feb 2025
EZDK Steel · Alexandria, Egypt
Level 2 Automation Engineer
Developed C# software components used in automation and process control across live plant systems
Managed Oracle databases — schema modifications, PL/SQL queries, and data extraction pipelines used by engineering teams daily
Maintained servers and network infrastructure in a high-availability industrial environment
Built and maintained reporting systems using Oracle Forms & Reports to support operational decision-making
C# Oracle PL/SQL Industrial Systems Network Infrastructure
Dec 2023 – May 2024
Remote
Freelance Python Developer
Built and deployed backend APIs for clients using FastAPI, Django, and Flask
Developed a Telegram bot that fetches live currency exchange rates and sends automated daily updates
Built a data scraping pipeline that extracts live football match data and exports it to structured CSV files
Delivered a desktop password manager with encrypted local storage and a GUI built with Python
FastAPI Django Flask Python REST APIs
Approach

Engineering philosophy

I enjoy building complete systems that solve real problems.

For me, a successful AI application is more than an accurate model. It also needs clean architecture, reliable APIs, maintainable code, reproducible workflows, and a user experience that makes the technology genuinely useful.

Whether I'm building an autonomous agent, a RAG system, or a computer vision application, I approach every project as a software engineering problem first. AI is one component of the solution, not the entire solution.

I value simplicity, modular design, measurable performance, and building systems that someone else could understand, maintain, and extend.

Active

Currently building

In progress
Enterprise Brain

A multimodal RAG platform that can understand technical documents, financial reports, tables, charts, and images using open-source LLMs and vision-language models.

In progress
DataPilot AI v2

Expanding the autonomous data analysis agent with improved planning, richer visualizations, and support for larger analytical workflows across multiple datasets.

Research
Warehouse Multi-Agent RL

Exploring cooperative reinforcement learning strategies for warehouse optimization under partial observability, focusing on coordination at larger agent populations.

Contact

Open to the right opportunity

I'm looking for roles where I can build AI systems that actually get used, I'm looking for roles where I can design and build complete AI-powered software systems, from backend services to intelligent applications. If you're working on something in AI engineering, LLM systems, backend development, or applied ML, I'd like to hear about it.

AI Engineering LLM Systems Backend Development Consulting Freelance Full-time Internships Remote Onsite Austria
Get in Touch
Quick Info
Location Linz, Austria
Availability Immediate
Work type Remote · Onsite Austria · Freelance
Education M.Sc. AI Eng. · JKU Linz
Languages Arabic · English · German