Federico Fiorio

About Me

As a passionate computer science major, I am dedicated to staying up-to-date with the latest tech advancements and learning new programming languages. My main interests are data science, machine learning, data engineering, and big data. With a strong analytical mindset and attention to detail, I excel in meticulously analyzing complex problems and extracting meaningful insights from data. Fueled by curiosity, I continuously seek knowledge and innovative approaches to tackle challenges in data science. During my free time, I enjoy tinkering with personal projects and engaging in sports activities, striking a balance between enjoying life and maintaining a strong commitment to developing my skills.

Experience

"Experience is the teacher of all things." - Julius Caesar

Data Engineer

05/2024 - Present

Consultancy based on AI, Big data and quantum.

Migration of DAGs Migrated DAGs from an old cloud composer with an obsolete airflow version to a new one, refactoring code and adapting it to 2.x airflow version
Data Pipelines & Historical Data Optimization: Designed high-volume data ingestion pipelines in Databricks, implementing Medallion Architecture for a fashion luxury brand. Replaced inefficient JOIN-heavy historical tracking with SCD Type 2, reducing query complexity and processing time by 100%, improving scalability, performance, and maintainability.
AI-Driven Document Retrieval: Developed RAG pipelines for a leading bank, leveraging vectorDB and OpenAI embeddings, and custom document techniques to improve document search accuracy by 20%.

Data Engineer Consultant

10/2023 - 04/2024

International consultant company, working mainly for financial institutions and banks.

Pivotal role in managing and maintaining an intricate web of ETL processes , establishing expertise in the orchestration of information through IBM infosphere DataStage
Proficient in SQL , leveraging its power to craft intricate queries, enhance database performance, and extract valuable insights
Collaborated closely with cross-functional teams to establish and enforce data governance policies
Elevated data quality standards through rigorous scrutiny and enhancement processes

Internship R&D

02/2021 - 05/2021

IT-centered company that develops personalized solutions for clients with focus on AR, VR and web applications.

Conducted extensive research on deep fakes and Generative Adversarial Networks (GANs) architecture
Strong focus on ethical considerations and responsible use of GANs technology during the research process

Education

"Education is the key to unlocking the world, a passport to freedom." - Oprah Winfrey

MSc Computer Science

10/2021 - 10/2023

Focus on Machine learning , AI, Data science and big data

Thesis on Membership inference attacks on text-to-image models
Sentiment analysis
Diffusion models for text-to-image generation
NLP
Data management, data retieval

ERASMUS+ Msc Degree

09/2022 - 02/2023

Computer vision traditional algorithms and CNNs
LLM theory and practice
Portfolio management and data analysis

Bachelor Degree Computer Science

10/2018 - 10/2021

Focus on computer science basics, networking , algorithms , data structures , DBMS , linear algebra , calculus and statistics

Thesis on generation of deepfakes through analysis and study of various python libraries

Technical Skills

"Technology is best when it brings people together." - Matt Mullenweg

Data Engineering

PySpark

89%

Airflow

89%

SQL Server

89%

IBM infosphere Datastage

83%

Machine Learning Frameworks

Scikit-learn

89%

Pytorch

83%

Tensorflow

95%

Programming Languages

Python

89%

Java

83%

Go

95%

C

89%

C#

83%

Javascript

95%

Data Visualization

Tableau

89%

Matplotlib

83%

Seaborn

95%

Cloud

Databricks

89%

BigQuery

89%

Composer

89%

GCS

89%

Cloud functions

89%

Certifications

"Any sufficiently advanced technology is indistinguishable from magic." – Arthur C. Clarke

Google Cloud

Machine learning engineer professional

Certification

AWS

Machine learning engineer specialty

Certification

Databricks

Certified Data Engineer Associate

Certification

Personal Projects

"The only way to do great work is to love what you do. If you haven’t found it yet, keep looking. Don’t settle." - Steve Jobs

RAG BGG

This app leverages AI to make board game rulebooks interactive and easily searchable, allowing users to upload PDFs and get instant clarifications. It also offers features like saved chats and game references, all while providing a smooth, Docker-based experience

Learn More

MSc Thesis

Text-to-image diffusion models attacks in scarce resource environments and privacy issues

Learn More

Complexity in board games

This study addresses the complex task of quantifying rulebook complexity in board games. By harnessing the data and APIs provided by BoardGameGeek (BGG), I feature engineered complex information not covered in BGG's definition and game rulebooks. Subsequently, I utilized machine learning algorithms to assign complexity scores to previously unknown rulebooks.

Learn More

NLP group project

understanding NLP and LLMs with hands-on experience

Learn More

Spaceship Mayhem

Infinite runner, I challenged myself in the creation of a videogame

Download APK

Algorithms for massive datasets

The purpose of this project is to implement a scalable solution for finding frequent itemsets (in our case pairs). In particular we implemented some of the algorithms used for market basket analysis (MBA) such as Apriori, PCY, Multi-Hash, Multi-Stage and SON

Learn More

Portfolio Management

Portfolio management basics through python

Learn More

Procedural content generation in Unity

Procedural content generation, specifically generating trees in a 3-D environment, AI applied to videogames.

Learn More

Audio pattern recognition with CNN

Recognizing others' feelings might be underrated. If one could adeptly navigate human emotions, they would gain a profound understanding of the person's needs, decipher the motives behind their words, and, in essence, comprehend the intended message more effectively

Learn More

Tableau vizzes

My Tableau experimentations

Learn More

Competitive Programming

Why I Love Competitive Programming

I enjoy sharpening my problem-solving skills through coding contests and algorithmic challenges. I regularly participate in LeetCode contests, explore new algorithms, and sometimes train on HackerRank too. I also maintain a repository of interesting problems and solutions, which you can check out below!

LeetCode Profile HackerRank Profile DSA GitHub Repo

EXTRA

"Go the extra mile; it's never crowded there." - Wayne Dyer

GCP profile

My google cloud badges

Learn More

LeetCode

My completed LeetCode problems, I like to keep myself sharp

Learn More