Edoardo is a data scientist who has worked as a CTO and vice president of engineering and founded multiple projects and businesses. He specializes in R&D initiatives, having created MLJ.ji (Julia's largest machine learning framework) and worked on detection algorithms at Shift Technology. Edoardo has a master's degree in applied mathematics from the University of Warwick.
Implemented multiple solidity smart contracts to handle auction mechanisms, sponsoring, and general NFT exchanges.
Built the containerized deployment process for Google Cloud Platform.
Implemented a social recommendation system for the users using graph theory and machine learning.
Implemented and maintained the Neo4j/GraphQL API, including writing multiple custom functions.
Created an API-based automated agent continuously extracting data from clients' sources, such as AWS, Azure, Google Cloud Platform, GitHub, and Google Workspace, into our storage awaiting processing.
Designed and implemented the graph structure on Neo4j to load clients' data, including infrastructure, assets, users, and permissions. It allowed the team to analyze complex relationships and find security flaws.
Outlined and developed a framework for the abovementioned graph, allowing developers and data scientists to easily extend the structure and add new analysis models for continuous improvement.
Created an automated vulnerability scanner running on clients' AWS and GCP clouds to continuously analyze their instances and report any new issues.
Researched and developed a machine-learning-based high-performance software in Rust capable of detecting shellcode cyber threats in raw network data.
Containerized the solution using Docker to make it easily deployable on-premise.
Built the company's entire cloud infrastructure on AWS.
Managed tech roadmaps, assigned tasks, and mentored junior developers.
Closed contract with one of the largest French cyber security companies to develop a specific cyber attack detection software.
Set up Neo4j and PostgreSQL databases with automated backup and security rules.
Set up isolated environments, firewall security rules, and a REST API with AWS Lambdas.
Included several AWS services with proper deployment using CloudFormation, such as AWS Lambda, SQS, SNS, Secrets Manager, S3, REST API, RDS, and AWS IoT.
Implemented state-of-the-art models to detect and read car license plates in pictures.
Researched and implemented new detection algorithms for specific types of fraudulent Italian claims.
Provided technical explanations and support during sales meetings in Italy for potential clients.
Created a pipeline to process, load, and analyze several gigabytes of raw data daily from our clients.
Set up the infrastructure made of a MySQL database and a Ubuntu server.
Set up CI/CD for continuous development and integration.
Designed and implemented the entire back-end logic.
Created a REST API to interact with the front and integrated the endpoints.
Learned CUDA and developed simulations using it to demonstrate speed gain against CPU.
Taught students what a GPU is, what CUDA is, and when you should consider it.
Participated in the development of CUDA.jl, the Julia CUDA wrapper.
A model was developed to detect shellcode, a cyber threat, in raw network data.
The model's primary focus was achieving a high detection rate with a low false positive rate.
The solution utilized Rust for a balance of speed, security, and vectorization, achieving 5Gbps on an average laptop with a detection rate of over 95% and a false positive rate under 0.000000001%.
Designed and implemented the first version of a unifying machine learning framework, aiming for a balanced interface that includes all models.
The project resulted in the integration of a dozen fundamental machine learning libraries, attracting attention from the Alan Turing Institute.
The project continues to be developed and is currently the 'MLJ.jl' framework.
Websek.co is a SaaS tool for security alerts on websites.
The project utilizes a REST API, AWS Lambda, EC2, and PostgreSQL for functionality.
Key components include an analysis tool, monitoring agent, and a Bootstrap/jQuery front end.
Implemented and studied a random interchange loop model for numerical analysis of quantum dynamics in ferromagnets.
Designed and implemented a C-based software capable of simulating a 160-lattice in a few seconds, significantly reducing simulation time.
The project involved a numerical model analysis to determine how environmental parameters affect quantum dynamics, utilizing a 4D lattice with increasing accuracy.
A Julia-based stock price prediction bot developed by a mathematics graduate.
The bot focuses on mid-to-long-term trading suggestions rather than real-time algorithmic trading.
The bot includes backtesting and various strategies, with some relying on machine learning and simpler signals.
A sentiment analysis classifier is being developed for processing and studying Tweets.
The classifier is designed to predict sentiment as positive, negative, or neutral.
The project involves researching and creating several classifiers for this task.
A software designed to automatically identify and notify users about train ticket price advantages.
The software scrapes data from multiple train ticket providers daily to find optimal deals.
It allows users to specify constraints like time periods and station changes for targeted price searches.
