Computer Engineer, specialized in LLM operations. I like to build webapps that integrate with AI!
Computer Engineer, specialized in LLM operations. I like to build webapps that integrate with AI!
info@giacomodandria.com
Esercizistem.com
Giacomodandria.com
linkedin.com/in/giacomodandria
Padova, Italy
huggingface.co/giacomodandria
github.com/giacomodandria
kaggle.com/giacomodandria
stackoverflow.com/u/14594459
info@giacomodandria.com
Esercizistem.com
Giacomodandria.com
linkedin.com/in/giacomodandria
Padova, Italy
huggingface.co/giacomodandria
github.com/giacomodandria
kaggle.com/giacomodandria
stackoverflow.com/u/14594459
ABOUT ME
In our world, artificial intelligence is reshaping not only how we look information up, but also we interact with the world around us, both digitally and physically. Building safe applications is top-of-mind, ensuring that their use case is properly offered and shielded from abuse to the final users.
ESL TEACHER, SOFTWARE DEVELOPER, Founder of giacomodandria.com January 2025 – Today
I taught hundreds of hours of English lessons on other language-learning and tutoring platforms provided by other companies. After a while, I realized I wanted to offer a more comprehensive experience for those looking to learn English in a way that blends a modern approach to language learning, as well as a classical one. This goal led me to design a hybrid model that combines online 1:1 lessons with an AI-powered companion web app that provides germane assistance to ESL students. The python-based web app (which I currently maintain and expand) is hosted on toolbox.giacomodandria.com, and streamlines the process of putting into practice various aspects of the English language. It contains many tools built with state-of-the-art Natural Language Processing techniques that enable learners to practice all the main skills necessary to master the language. I am mainly focused on backend development and data integration, harnessing (mostly) automated elements for the frontend UI. The app includes an ever-growing toolbox of tools, accessible through an app-like interface, and offers cross-platform compatibility for both mobile and desktop.
During my time at Cardinal LLC, I led an R&D project aimed at creating a recommendation engine that analyzes and profiles user data regarding past searches on the Freename.io web3 domain registrar platform. The developed system is able to intelligently provide personalized and relevant recommendations for similar search terms the user might be interested in. I opted for a combination of open-source and commercially available generative models such as Google’s Gemma, Meta’s Llama 3, Mistral AI’s Mixtral, as well as OpenAI’s GPT 3.5/4/4o, Google’s Gemini 1.0/1.5 and Anthropic’s Claude that can be seamlessly switched from one to the other using the developed API. The final phase focused on the real-time implementation and testing of the recommendation engine using FastAPI in a Dockerized environment, leading to accurate recommendations for each user. Throughout the project, I conducted an in-depth analysis of both open-source and commercial Generative AI models which were ultimately included in the final report for the project, along with examples of generated outputs that significantly enhanced the user experience and service optimization.
MACHINE LEARNING ENGINEER, INTERN Cardinal LLC, Padova, Italy February 2024 – May 2024
MACHINE LEARNING ENGINEER, INTERN Cardinal LLC, Padova, Italy February 2024 – May 2024
During my time at Cardinal LLC, I led an R&D project aimed at creating a recommendation engine that analyzes and profiles user data regarding past searches on the Freename.io web3 domain registrar platform. The developed system is able to intelligently provide personalized and relevant recommendations for similar search terms the user might be interested in. I opted for a combination of open-source and commercially available generative models such as Google’s Gemma, Meta’s Llama 3, Mistral AI’s Mixtral, as well as OpenAI’s GPT 3.5/4/4o, Google’s Gemini 1.0/1.5 and Anthropic’s Claude that can be seamlessly switched from one to the other using the developed API. The final phase focused on the real-time implementation and testing of the recommendation engine using FastAPI in a Dockerized environment, leading to accurate recommendations for each user. Throughout the project, I conducted an in-depth analysis of both open-source and commercial Generative AI models which were ultimately included in the final report for the project, along with examples of generated outputs that significantly enhanced the user experience and service optimization.
ENGLISH SECOND LANGUAGE TEACHER January 2024 – Present
Over the years, I have developed a very deep passion for the English language, and in an effort to make it accessible to other people, I started to teach online lessons during my spare time while at university. I ended up teaching more than 700 hours, 500 of which were as a partner teacher on the GoStudent platform.
My Bachelor’s thesis explores the feasibility of an ML-based system for real-time physical exercise repetition counting. Leveraging either webcams or external recording devices— even those with moderate processing capabilities—the proposed system extracts joint coordinates from the video feed, allowing for both movement classification and repetition counting. Initial results demonstrate accurate repetition counting in many scenarios, despite potential shortcomings attributed to the use of a limited training dataset. The system incorporates a variety of classical algorithms, including Logistic Regression (LR), Stochastic Gradient Descent (SGD) Classifier, Random Forest (RF), Multinomial Naive Bayes (MNB), Gaussian Naive Bayes (GNB), K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), and a Multi-Layer Perceptron (MLP) Classifier. All those algorithms were taken from the sci-kit learn library, while the extraction of the joints coordinates was done through Google’s MediaPipe library that leverages on-device machine learning.
BACHELOR’S THESIS University of Padova, Padova, Italy January 2023 – August 2023
BACHELOR’S THESIS University of Padova, Padova, Italy January 2023 – August 2023
My Bachelor’s thesis explores the feasibility of an ML-based system for real-time physical exercise repetition counting. Leveraging either webcams or external recording devices— even those with moderate processing capabilities—the proposed system extracts joint coordinates from the video feed, allowing for both movement classification and repetition counting. Initial results demonstrate accurate repetition counting in many scenarios, despite potential shortcomings attributed to the use of a limited training dataset. The system incorporates a variety of classical algorithms, including Logistic Regression (LR), Stochastic Gradient Descent (SGD) Classifier, Random Forest (RF), Multinomial Naive Bayes (MNB), Gaussian Naive Bayes (GNB), K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), and a Multi-Layer Perceptron (MLP) Classifier. All those algorithms were taken from the sci-kit learn library, while the extraction of the joints coordinates was done through Google’s MediaPipe library that leverages on-device machine learning.
FREELANCE WORDPRESS DEVELOPER Self-employed January 2022 – January 2025
I have developed various WordPress-based websites for some clients as well as for myself. Among the ones I created for my own use there are:
Esercizistem.com: meant to help students understand and solve complex math problems of Mathematical Analysis 1/2 (Calculus 1/2) and Linear Algebra and Geometry. The website also stores my notes (in Italian) from some of the coursed I took while studying during my Bachelor’s degree. Some of the components in the website are custom-made using HTML/CSS/JavaScript.
Giacomodandria.com: contains various notes (in English) from courses I took during university, and it has since become the current website in use for 1:1 private English lessons.