Athanasios Masouris

AI Engineer

Resume

About Me


I'm a passionate professional with a strong academic background, holding a master's degree in Computer Science from the Delft University of Technology and a master's degree in Electrical and Computer Engineering from the National Technical University of Athens. My interest lies in the fields of Artificial Intelligence, Machine Learning, and Computer Vision.

Experience


Placeholder image

AI Engineer

PwC Greece
-

Placeholder image

Contributor

Google Summer of Code @ Intel OpenVINO Toolkit
-

Project: Train a DL model for synthetic data generation for model optimization

Python PyTorch OpenVINO Flask API HTML JS Deep Learning Computer Vision Generative Adversarial Networks (GANs) Knowledge Distillation Model Quantization LaTeX
Placeholder image

Military Service

Hellenic Army
-

  • Digitized archived documents
  • Developed scripts to automate the generation of patrol schedules
Python MS EXcel VBA
Placeholder image

Machine Learning Intern

NCSR DEMOKRITOS
-

Project: Automatic Video-Game Review Summarization

  • Refactored and rewrote the entire codebase of the pipeline for the review summarization system in Python
  • Evaluated machine learning classifiers for identifying the reviewed aspects of the video-game in users' reviews
  • Proposed a meta-classification approach which improved the overall performance of the pipeline
Python PyTorch Scikit-learn Natural Language Processing (NLP) Classification Embeddings

Projects


Placeholder image
RAGPal: A PoC RAG-based virtual assistant
RAGPal is implemented as a web application with a front-end interface for user interaction and a FastAPI-based back-end for handling requests and business logic. The system utilizes Azure OpenAI API resources for chat completion and embedding generation, and the Qdrant vector database to serve as the knowledge base for storing and retrieving documents. View more..
Python FastAPI AzureOpenAI API Qdrant HTML/CSS JavaScript Large Language Models (LLMs) Retrieval Augmented Generation (RAG) Prompt Engineering
Placeholder image
End-to-End Chess Recognition
The goal of this project was to develop a methodology that would predict the chessboard configuration in an input image of a chessboard. Contrary to the predominant approaches, that aim to solve this task through the pipeline of chessboard detection, square localization, and piece classification, we relied on the power of deep learning models to directly predict the configuration from the entire image. View more..
Python PyTorch Lightning Deep Learning Computer Vision Image Processing
Placeholder image
Chess Recognition Dataset (ChessReD)
The Chess Recognition Dataset (ChessReD) is a comprehensive collection of images of chess formations that were captured using various smartphone cameras. It comprises 10,800 images from 100 chess games. The dataset features a wide range of chess piece configurations, captured under different angles and lighting conditions. The dataset includes detailed annotations about the pieces' formations in chess algebraic notation, providing valuable information for chess recognition research. View more..
Deep Learning Computer Vision Chess Recognition Object Detection
Placeholder image
TeleGAN: Text-To-Image Synthesis using GANs
The goal of this project was to develop a novel architecture which would be able to generate high-resolution images conditioned on a given text description. The proposed model (TeleGAN) decomposes the difficult task of high-quality image generation, into the more manageable sub-problems of low-res black-and-white image generation, colorization, and resolution enhancement, in three consecutive stages. View more..
Python PyTorch Deep Learning Computer Vision Conditional Image Generation Text-to-Image Generative Adversarial Networks (GANs)
Placeholder image
Other projects
The rest of my projects can be found on my GitHub account.

Education


Delft University of Technology

MSc in Computer Science
-

  • Track: Artificial Intelligence
  • Grade: 8.5/10 (Cum Laude)
  • Thesis: End-to-End Chess Recognition
TU Delft

National Technical University of Athens

Joint BSc & MSc in Electrical and Computer Engineering
-

  • Concentration field: Computer Science
  • Grade: 8.27/10
  • Member of the Artificial Intelligence and Learning Systems Laboratory (AILS lab)
  • Thesis: Text-to-image synthesis using Generative Adversarial Networks (GANs)
NTUA

Certificates

  • Machine Learning Engineering for Production (MLOPs) (Nov. 2023) by deeplearning.ai [credential]
  • Azure AI Fundamentals (May 2023) by Microsoft [credential]
  • Azure Fundamentals (May 2023) by Microsoft [credential]
  • Deep Learning Specialization (Aug. 2019) by deeplearning.ai [credential]
  • Machine Learning (Apr. 2019) by Stanford|Online [credential]

Publications


  1. Athanasios Masouris and Jan van Gemert (2024). End-to-End Chess Recognition. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pages 393-403
    [SciTePress] [arXiv]

Skills


Programming/Scripting Languages
  • Python
  • SQL
  • HTML/CSS
  • JavaScript

Machine Learning Frameworks & Libraries
  • PyTorch
  • PyTorch Lightning
  • Scikit-learn
  • OpenCV

Frameworks and tools
  • Azure
  • Docker
  • Git
  • REST APIs
  • Django
  • LaTeX

Contact