Francesco Fontan
Verified Expert in Engineering
Data Scientist and Developer
Francesco is a seasoned data scientist with robust analytical and technical capabilities. His area of interest is tackling business problems using traditional machine learning and deep learning for computer vision or natural language processing (NLP) tasks. Fascinated by operational research, optimization, and GPU-accelerated computing, Francesco has a strong machine learning and cloud engineering background that helps him drive conversations and coordinate heterogeneous teams.
Portfolio
Experience
Availability
Preferred Environment
Linux, Python 3, Pandas, Scikit-learn, TensorFlow, PyTorch, Hugging Face
The most amazing...
...thing I've developed is a scheduling tool for a cruise company using forecasting and optimization, saving $2 million per year.
Work Experience
Data Scientist
Levi Strauss & Co.
- Implemented a system that proposes the most effective promotions for all US stores, such as buy one get one or X% off. This system optimized key business KPIs (margin increased by at least 2 – 3%) and provided valuable insights.
- Led the technical global promotion team, providing recommendations for five global markets for retail stores, outlets, and eCommerce, creating value of around $20 million in additional revenue annually.
- Redesigned the pricing recommendation tool, increasing speed by six times using BigQuery and Apache Airflow.
- Supported the migration from AWS to Google Cloud Platform (GCP), coordinating the work between data engineers and machine learning (ML) engineers.
- Developed a GenAI product description generator for 2,000+ items and 20+ languages with PaLM2 and Imagen.
Data Scientist
Delivery Hero
- Designed the first version of the picker scheduling tool that optimized the shifts of the people working in dark stores leveraging Python and mixed-integer programming (MIP), reducing the costs by more than $1 million per year.
- Prototyped the first version of a smart location-based inventory that suggests where to place items optimally to minimize the picking time and other operational activities inside a warehouse.
- Created automated pipelines for autoformatting using Python and SQL codes based on custom rules, helping data scientists to speed up deploys to two hours per person per sprint and bringing uniformity across different teams.
Data Scientist
Machine Learning Reply
- Created text classification to analyze emails automatically, speeding up the entire business process by ten times.
- Designed an optimization tool for a cruise company that handles embarking and disembarking for more than 50,000 people, resulting in estimated average savings of $1 million annually.
- Conducted ten lectures for the course "AI and ML: Platforms and vendor solutions" to graduate students enrolled in the second-level master studies in artificial intelligence and cloud at the Polytechnic University of Turin.
- Worked on a recommender system for Reply's internal social network using traditional collaborative filtering methods, item-based models, and NLP techniques. The algorithms handled over 10 thousand active daily users and increased engagement by 10%.
- Redesigned an ML model for swaption prices, achieving better performance by decreasing the mean squared error (MSE) by 10% compared to the previous implementation and lowering the RAM required by 30%, with an increased speed by 1.5 times.
- Built a system to detect and classify various road defects, as predictive maintenance applied to highway asphalt is crucial to cut costs. This object detection model was based on YOLOv5.
- Organized and delivered more than 20 Nvidia courses on the latest in machine learning and deep learning as an experienced instructor.
Data Scientist
Evo Pricing
- Onboarded two major customers with revenues exceeding $1 billion, showcasing my ability to build strong relationships and deliver value to high-profile clients.
- Implemented automation for initial analysis during customer onboarding, reducing development and analysis time from 25 days to just three days, enabling swift and accurate evaluation of elasticities, sales trends, product segmentation, and inventory.
- Architected a computer vision system that effectively recognized similar competitor products using images. This implementation enhanced the accuracy of our competitor data, leading to improved forecasting algorithms (-5% MSE).
Experience
NLP Ticketing System
This system analyzed emails received from customer support and logs from the network infrastructure, extracting useful information using NLP techniques and LLMs to open, assign, and finally close tickets fully automatically.
This automation increased the speed by ten times, predicting more than ten ticket fields with an average accuracy of 90%. Finally, the pipeline could scale: training was performed on half a million records, while the inference module handled more than 20 tickets per hour.
CV for Predictive Maintenance
This solution harnesses an object detection model, utilizing Yolo v5, in conjunction with external data points pertinent to the road section under scrutiny, such as traffic patterns and weather conditions.
Notably, the recall rate surpassed 80%, and the tool achieved significant cost savings of 600,000 euros in its inaugural year of operation.
Chatbot QA
Smart Planning for a Cruise Line
I designed a Python tool based on Google OR-Tools, an optimization suite by Google AI, able to solve MIP problems that involved more than 30,000 embarks every year, obtaining an estimated average saving of 10%, corresponding to $1 million per year.
NVIDIA Instructor
Courses Delivered:
Fundamentals of Deep Learning
Building Transformer-Based Natural Language Processing Applications
Building Intelligent Recommender Systems
Fundamentals of Accelerated Data Science with RAPIDS
Fundamentals of Deep Learning for Multiple Data Types
Fundamentals of Accelerated Computing with CUDA Python and C/C++
Optimizing Budget Allocation
To achieve this, we crafted forecasting models that meticulously analyzed ticket sales over time, factoring in external variables such as weather, competitor actions, and specific events. Additionally, we engineered a system capable of predicting future visitor numbers based on a set of marketing campaigns.
Through these efforts, we estimated an annual cost savings of approximately $300,000.
Swaption
Additionally, I achieved resource optimization by slashing RAM requirements by an impressive 30% while accelerating model processing by a factor of 1.5x. To fortify the model's reliability, I strategically employed Ensemble methods, harnessing the strengths of XGBoost, Random Forest, and Neural Network techniques.
Rec Sys for Internal Social Network
active daily users.
Optimization of Budget Allocation
I was the technical team leader in this project that aimed to define a tool capable of suggesting how to distribute, in the most effective way, the budget between marketing campaigns to increase volumes and more aggressive pricing policies to increase the conversion rate.
We developed forecasting models to analyze the tickets sold over time and consider external factors such as weather, competitors, and particular events. But also a system able to predict the number of visitors in the future given a set of marketing campaigns. Finally, we estimated a cost saving of around $300,000 per year.
NLP for Voicebot
Generative AI for Product Descriptions in eCommerce
Dynamic Pricing in Retail
Bundle Promotion Optimization
Skills
Languages
Python 3, Python, R, C++, SQL
Libraries/APIs
Pandas, Scikit-learn, TensorFlow, PyTorch, Keras, SpaCy, RAPIDS, XGBoost, Dask
Tools
ChatGPT, Apache Airflow, Looker, Azure OpenAI Service, MATLAB, You Only Look Once (YOLO), Whisper
Paradigms
Data Science, DevOps
Platforms
Google Cloud Platform (GCP), Linux, Docker, Amazon Web Services (AWS), Databricks, Azure, Twilio, NVIDIA CUDA, Kubeflow
Other
Statistics, Probability Theory, Deep Learning, Machine Learning, Optimization, Natural Language Processing (NLP), Computer Vision, Machine Learning Operations (MLOps), Pricing, Artificial Intelligence (AI), GPT, Generative Pre-trained Transformers (GPT), Data Modeling, Data Analysis, Language Models, Big Data, Time Series, Chatbot, Large Language Models (LLMs), Open-source LLMs, OpenAI, Hugging Face, Network Science, Forecasting, Bots, Email, CI/CD Pipelines, Data Analytics, Marketing Analytics, Software Architecture, Containerization, Promotion, Cloud, Data Engineering, GPU Computing, Text Classification, Reinforcement Learning, Categorization, Regression, Unsupervised Learning, Dynamic Pricing, Computer Vision Algorithms, BERT, Neural Networks, Torch, Object Detection, Predictive Modeling, FastAPI, Voice Chat, Chatbots, Recommendation Systems, Financial Engineering, Collaborative Filtering, Financial Analysis, LangChain, Sales Forecasting, Llama 2
Education
Master's Degree in Mathematical Engineering
Polytechnic University of Turin - Turin, Italy
Bachelor's Degree in Mathematics and Computer Science
Polytechnic University of Turin - Turin, Italy
Certifications
TensorFlow Developer Certificate
TensorFlow
Professional Machine Learning Engineer
Google Cloud
Professional Data Engineer
Google Cloud
Deep Learning Institute Certified Instructor
NVIDIA
Microsoft DAT257x: Reinforcement Learning Explained
edX
Deep Learning
DeepLearning.AI
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