TABLE OF CONTENTS⌗

• Work Experience
• Education
• Technical Skills
• Languages
• Download PDF

WORK EXPERIENCE⌗

· Software Developer Apprentice⌗

5 September 2024 - Present

Aitho S.r.l. – Catania, Italy

Backend Development:⌗

• development of backend applications in Python (Flask, FastAPI);
• design and development of vector databases (QDrant, Neo4J, MongoDB) and non-vector databases (MySQL, Postgresql).

Data Science:⌗

• development of solutions based on reactive RAG agents using the LangChain framework;
• advanced prompting for reactive RAG agents (with LLMs such as GPT, Claude, DeepSeek, etc.);
• design and implementation of multi-agent system architectures
• delivery of university seminar about LangChain and cutting-edge AI/LLM technologies (Agent-to-Agent, MCP);
• MLOps with MLFlow, Arize AI Phoenix, Langfuse.

DevOps/System Administrator:⌗

• service hosting (Traefik, nginx, Istio);
• development of automated CI/CD pipelines for builds (Woodpecker);
• maintenance and development of architectures via Ansible;
• management of Kubernetes clusters.

· Internship: Backend Dev & Data Scientist⌗

21 February 2024 - 20 August 2024

Aitho S.r.l. – Catania, Italy

• Backend training (Java, SpringBoot).
• Backend software development.
• RAG architecture design and development using the following technologies:
  • Python;
  • Google Cloud Platform;
  • Azure API (Sharepoint);
  • Git API (Gitea);
  • LangChain;
  • Google Gemini.
• CI/CD management for deployments.
• Backend development of external integrations for LLM chatbots through the following technologies:
  • TypeScript;
  • NextJS;
  • Google Drive API;
  • Slack API;
  • Vercel;
  • Supabase;
  • Pinecone.
• Backend development for LLM chatbot on Slack.
• MongoDB backend design and development.

· Curricular Research Internship⌗

3 April 2023 - 10 June 2023

UNICT - Laposs – Catania, Italy

• Study of large unstructured data analysis techniques (text, web data, digital activity logs, etc.).
• Learning advanced data analysis techniques (e.g., Machine Learning) for extracting information from data provided by companies that participated in the project.
• Learning techniques for measuring a company’s “reputation,” e.g., in terms of sustainability, and the “sentiment” expressed on social media regarding the products/services offered by the same company.
• Involvement in multidisciplinary working groups, with students from other departments (e.g., Dept. of Mathematics and Computer Science), professionals and industry experts.
• Qualitative evaluations on the outputs of the algorithms used and based on these evaluations propose possible modifications to the input data and/or analysis techniques.

EDUCATION⌗

· Computer Science Master’s Degree⌗

October 2021 - 14 December 2023

Università degli Studi di Catania – Catania, Italy

Thesis: Knowledge extraction from sustainability reports using computer vision-based heuristics

Grade: 110/110 cum laude

Nominee “Premio Archimede” 20th Ed. 2024

· Computer Science Bachelor’s Degree⌗

October 2017 - 23 April 2021

Università degli Studi di Catania – Catania, Italy

Thesis: Sviluppo di add-on per Blender: applicazioni nell’archeologia e nell’ingegneria edile

Grade: 103/110

· Scientific Lyceum Diploma⌗

2012 - 2017

Liceo Scientifico A. Volta – Caltanissetta, Italy

Grade: 87/100

PUBLICATIONS⌗

· Abstracting Stone Walls for Visualization and Analysis⌗

February 2021

G. Gallo, F. Buscemi, M. Ferro, M. Figuera, P. M. Riela - Pattern Recognition. ICPR International Workshops and Challenges (pp.215-222)

An innovative abstraction technique to represent both mathematically and visually some geometric properties of the facing stones in a wall is presented. The technique has been developed within the W.A.L.(L) Project, an interdisciplinary effort to apply Machine Learning techniques to support and integrate archaeological research. More precisely the paper introduces an original way to “abstract” the complex and irregular 3D shapes of stones in a wall with suitable ellipsoids. A wall is first digitized into a unique 3D point cloud and it is successively segmented into the sub-meshes of its stones. Each stone mesh is then “summarized” by the inertial ellipsoid relative to the point cloud of its vertices. A wall is in this way turned into a “population” of ellipsoid shapes statistical properties of which may be processed with Machine Learning algorithms to identify typologies of the walls under study. The paper also reports two simple case studies to assess the effectiveness of the proposed approach.

TECHNICAL SKILLS⌗

• Operating Systems:

  • Linux
  • Windows

• Programming Languages:

  • Python
  • C/C++
  • Java

• DevOps:

  • Docker
  • Woodpecker
  • GitHub Actions
  • Ansible
  • Kubernetes

• Code Management

  • Git
  • Gitea
  • GitHub
  • GitLab

• Backend development

  • API Management and design
  • Database Management and design
  • Server-Side Development

• Cloud Computing

  • Google Cloud Platform

• 3D Graphics and Modelling

  • Blender

• Artificial Intelligence

  • Machine/Deep Learning
  • Computer Vision
  • Large Language Model (LLM)
  • Retrieval-Augmented Generation (RAG)
  • Advanced Prompting

LANGUAGES⌗

DOWNLOAD PDF⌗

· Europass Format (ITA)⌗

· Europass Format (ENG)⌗

▴ TABLE OF CONTENTS⌗