Explore my GitHub repositories and pages: featuring tutorials, personal projects, and ongoing developments in data science, machine learning, and software development. I am continuously uploading new projects to demonstrate my skills and growth.
Showcases a diverse range of tutorials, personal projects, and technical resources aimed at demonstrating my skills.
IEEE CISOSE (ISADS) — International Symposium on Autonomous Decentralized Systems. Applying deep reinforcement learning and Kolmogorov-Arnold Networks to multi-agent vehicle pursuit in urban simulation environments.
An AI-powered outbound calling agent built with ElevenLabs that contacts prospective customers with personalized offers — retrieving client data in real time, presenting pre-approved credit lines, and activating services live on the call through Azure Functions.
A multi-agent AI platform embedded in Slack that automates high-demand internal processes — document generation, credit-line increases, and assignment workflows — using Google ADK for agent orchestration, GPT-4.1 models for reasoning, and Azure Container Apps for serverless execution.
An end-to-end event-driven pipeline built on Azure Service Bus that ingests call center recordings, transcribes audio to text, and leverages generative AI to produce structured summaries, payment-intent scores, and agent-performance metrics — deployed to production with 80–85% content accuracy.
Project Overview This project showcases the development of a chatbot designed to assist users with labor-related queries, including conciliation processes, workers’ rights, employer responsibilities, and conciliator training. It was developed in two phases:
A serverless Azure Function that uses LLM vision models to extract, categorize, and normalize data from customer receipt images — replacing manual extraction with 85–90% accuracy and reducing analyst workload by 70%.
Project Overview This project, developed as part of the “Principles of Deep Learning” course in the Master’s in Data Science program, focused on building a speech generator using deep learning techniques, specifically transformers. The model was fine-tuned with presidential speeches and related materials to produce coherent text outputs.
Project Overview This project, developed as a part of the “Cloud Computing” course in the Master’s in Data Science program, demonstrates an automated news analysis system using various Google Cloud Platform (GCP) services. The objective was to create a scalable, serverless solution for extracting, processing, and analyzing news articles from popular media outlets.
Reasearch paper publication.
Project Overview The Secure Chat Application is an advanced messaging system built in Java, designed to demonstrate the practical application of cryptographic techniques in ensuring secure communication. The project includes a client-server architecture, a Public Key Infrastructure (PKI) for certificate and key management, and multiple encryption methods for message confidentiality, integrity, and authenticity.
Overview The ADSOA Calculator Project is an implementation of the Autonomous Decentralized Service-Oriented Architecture (ADSOA) to create a system capable of handling arithmetic operations. The project is built to demonstrate the principles of distributed systems, fault tolerance, and service-oriented architecture, applying these to a simple yet robust calculator application.