I am passionate about technologies and enjoy taking on complex projects and transforming ideas into a fully-functional applications that are both user-friendly and impactful. I'm also pursuing a Master's degree in Computer Science at the University of Colorado-Boulder to refine my skills and deepen my focus on creative problem-solving.

📊 Vasilios.io, a web application that scrapes data from a public internet archive of software engineering and data science articles, analyzes and visualizes the results of the data, including NLP and data analysis.

• Automated web scraper: Airflow, RabbitMQ, PostgreSQL, Python, Scrapy, deployed on AWS (public repo coming soon)
• Interactive NLP Dashboard:
  • Tech Stack: Python, Django, HTML/CSS, JavaScript, PostgreSQL, Docker, deployed on AWS
  • The system fetches data through RESTful API from the database, analyzes the data with data analysis and NLP libraries (NumPy, Pandas, NLTK, etc.), and visualizes the dashboard on the frontend with Chart.js

🤖 AI projects, this is where I post my most recent experimentations with AI frameworks, mainly RAG, Agents, and LLMs

• AI Analyst Agent web app
• Chat with your PDF web app

🛍️ Fashion Recommender System, a system that detects fashion objects and learns image representations through Neural Networks. It also utilizes ANN similarity search index to retrieve and rank these image representations.

• Models used: YOLOv5, Convolutional Autoencoder
• Vector Store: FAISS Flat Index
• Object Detection Model Repo, the object detection model was used to detect fashion objects and obtain bounding box coordinates
• Embedding Model Repo, the model then obtain a 512-dimensional embedding of each detected fashion objects with an embedding model, and utilized an ANN algorithm to find the top-k similar images based on their vector embeddings

📑 Deep Learning Notebooks

• It currently contains my notebooks related to my experiments with different models and algorithms while working on the fashion recommender project above.
• Image Classification with CNN (multiclass classification)
• Image Segmentation with UNET and a pretrained ResNet backbone (multilabel classification)
• Feature Extraction with pre-trained ResNet18 architecture (fashion-recommender-v1)
• ANN Similarity Search Index comparisons (fashion-recommender-v1)

📺 Movie Recommender System , built a two tower model using TensorFlow and Netflix Dataset

🐉 Mini Adventure Game, my first mini project with Python

📊 An Analysis of Bike Services Data with R

💻 An analysis of Yelp Reviews with SQL

Linkedin