Luca Puggini
Verified Expert in Engineering
Data Scientist and Developer
Rome, Metropolitan City of Rome, Italy
Toptal member since December 4, 2020
Luca is a senior data scientist with a Master's degree in mathematics, a Ph.D. in machine learning, and several years of industry experience. He worked at Intel and the University of Bergen, and developed tools for network performance monitoring in high-frequency trading, data-driven algorithms for production optimization in semiconductor manufacturing, and anomaly detection applied to network security. Luca excels with complex AI projects from the research phase to deployment and production.
Portfolio
Experience
- Data Science - 10 years
- Artificial Intelligence (AI) - 8 years
- Statistics - 8 years
- Machine Learning - 8 years
- Python - 7 years
- Pandas - 6 years
- NumPy - 6 years
- SQL - 4 years
Preferred Environment
Scikit-learn, SQL, Pandas, NumPy, Artificial Intelligence (AI), Machine Learning, Python
The most amazing...
...software I've developed recognizes users from their network traffic and contained 30,000+ lines of Python code.
Work Experience
Digitail Innovation Coordinator
TechnipEnergies
- Developed a tool that automatically completes engineering 3D models.
- Created a tool using Large Language Models that finds the best matches between documents.
- Managed a team of seven data scientists and software engineers.
Data Scientist | Consultant
Freelance
- Developed A/B testing and other statistics for an eCommerce plugin vendor to optimize conversion rate.
- Helped a consulting company to enter the data-science industry.
- Estimated the effect of water filters on the population's health in African villages.
- Developed a chatbot for eCommerce using ChatGPT and LLM.
Vice President Data Scientist | Technical Lead
Pico
- Served as the technical referent for data science for the whole company.
- Developed a database containing market tick data (700 tera) and used it for computing trading metrics.
- Oversaw and participated in the development of large software projects mainly focused on big data and data science.
Assistant Vice President Data Scientist
Pico
- Developed tools for network performance monitoring in the high-frequency trading domain.
- Built a REST API using Flask, enabling users to interact with product systems and to consume the generated data.
- Ensured that all the shipped software was bug-free and able to scale as required.
Data Scientist
Corvil
- Developed software to recognize users from their network traffic. Created 30,000+ lines of Python code containing advanced machine learning algorithms and highly optimized data pipelines.
- Developed several data-based products mainly focused on anomaly detection applied to network security.
- Tested the developed products, ensuring both statistical accuracy and scalability under heavy loads.
Demonstrator
Maynooth University
- Demonstrated and tutored students of the C++ course for the Electronic Engineering Department of Maynooth University.
- Evaluated students' skills in embedded C++ development.
- Helped students to improve their C++ software development skills.
Medical Statistician (Contract 20%)
University of Bergen
- Investigated the relationship between menopause and asthma.
- Analyzed data using classical statistical inference and epidemiological techniques.
- Created visualizations to make results consumable to non-data-savvy users.
Visiting Researcher
Intel
- Researched and developed new data-driven algorithms for production optimization in semiconductor manufacturing.
- Developed an anomaly detection algorithm for optical emission spectroscopy high dimensional data collected during plasma etching.
- Developed a supervised and unsupervised variable selection algorithm to reduce the cost of data collection.
Experience
User Recognition
Anomaly Detection for Large Scale Network Data
A/B Testing for eCommerce SaaS
Education
Ph.D. in Data Science
Maynooth University - Maynooth, Ireland
Master's Degree in Mathematics and Computer Science
Tor Vergata University - Rome, Italy
Bachelor's Degree in Mathematics
Tor Vergata University - Rome, Italy
Skills
Libraries/APIs
NumPy, Pandas, Scikit-learn, XGBoost
Tools
ChatGPT, STATA
Languages
Python, Python 3, SQL, R, Bash, Bash Script, JavaScript, C++
Paradigms
ETL, REST, Anomaly Detection
Platforms
Jupyter Notebook, Docker, Amazon, Amazon Web Services (AWS), Arduino
Storage
Data Pipelines, Data Lakes, Databases, JSON, Data Lake Design, PostgreSQL
Industry Expertise
High-frequency Trading (HFT)
Other
Machine Learning, Artificial Intelligence (AI), Mathematics, Statistics, Data Science, APIs, Data Engineering, Data Analytics, Statistical Analysis, Data Modeling, Data Visualization, Multivariate Statistical Modeling, Time Series Analysis, Data Analysis, Model Development, Classification Algorithms, Data Mining, Data Reporting, Real-time Data, Technical Hiring, Source Code Review, Code Review, Task Analysis, Interviewing, Dashboards, Data Wrangling, Jupiter, Data Collection, Datasets, Product Analytics, Product Development, Predictive Modeling, Statistical Modeling, API Integration, Natural Language Processing (NLP), OpenAI GPT-4 API, Large Language Models (LLMs), OpenAI, Mentorship & Coaching, Consulting, Time Series, Forecasting, Technical Leadership, Leadership, Prompt Engineering, Minimum Viable Product (MVP), Architecture, Software Architecture, Bots, Back-end Development, Machine Learning Operations (MLOps), Retrieval-augmented Generation (RAG), Probability Theory, Neural Networks, Team Management, A/B Testing, Pricing, Pricing Strategy, Team Leadership, Finance, OpenAI GPT-3 API, Transformer Models, Chatbots, Numerical Methods, Bayesian Statistics, Sensor Data, Algorithmic Trading Analysis, Deep Learning, Computer Vision, Financial Forecasting, Generative Pre-trained Transformers (GPT)
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring