This website is a work in progress. Check back soon for more updates!
Cristian Desivo
I'm a mathematician, a python expert and an AI developer. I've been working as a freelance developer since 2016, mastering the art of mathematical optimization, python and AI.
Check out the summaries of some of the projects I've worked on below, send me an email at cdesivo92@gmail.com, or hire me on freelancer.com
Hire me
Past projects
Large Language Models: Integration of LLMs into Applications
This project involves integrating LLMs into various applications to enhance their capabilities through natural language processing, text generation, and conversational AI. These integrations have been applied in different domains, including poll generation based on subject matter and target audience, and developing chatbots for customer support and information retrieval.
View Details
Deep Learning Computer Vision for Workplace Monitoring
The project involves using deep learning and computer vision to monitor workplace stations and count people entering and leaving a specified area. A camera setup captures video streams, which are processed in real-time to detect and verify people. A Python GUI developed with PyQt5 aids in tagging data for training the model. The training process is conducted using TensorFlow, and the trained model is deployed to a Jetson Nano for real-time inference.
View Details
Mathematical Optimization Projects
The projects involve solving a variety of optimization problems using mathematical and metaheuristic approaches. These include combinatorial optimization, genetic algorithms, and job shop scheduling. By employing Python and specialized optimization libraries, these projects aim to find efficient and high-quality solutions to complex problems.
View Details
Single-Player 2D Games in Unity
These projects involve designing procedurally generated levels, implementing various gameplay mechanics, and ensuring a compelling player experience. The games are characterized by permadeath, random level generation, and challenging gameplay, typical of the roguelike genre.
View Details
Data Extraction and Report Generation
The project involves creating a Python script that extracts data from Excel, Word, text, and CSV files to generate reports based on specific client requirements. The script features a GUI developed with PyQt5, enabling users to select input files and specify the output directory for the reports. The GUI ensures ease of use, providing options to customize the report generation process.
View Details
Reinforcement Learning with computer vision
The project involved developing a reinforcement learning system to optimize a specific task within a complex driving simulation environment. The system utilized computer vision techniques to process visual input data and make decisions based on the environment's state. The goal was to train an agent to navigate the environment efficiently and achieve a set of predefined objectives.
View Details
Electrical Engineering: Designing Circuits as Neural Networks
The project involves designing circuits that function as neural networks. These circuits emulate the behavior of biological neurons and synapses, performing essential neural network operations such as weighted sum calculations, activation functions, and signal propagation. The training of these circuits can be conducted either directly on the hardware or through comprehensive software simulations using SPICE tools.
View Details
Simulated Flight Instruments on Raspberry Pi
The project involves using Flask to create a web-based interface where users can input flight data, and Pygame to simulate and display realistic flight instruments that respond to these inputs in real-time. The system is designed to provide an immersive and interactive experience, allowing users to see how changes in flight parameters affect the instruments.
View Details