Gregory Vial
Verified Expert in Engineering
Software Developer
Gregory is a software engineer with a passion for machine learning. He has managed large projects and virtual international teams throughout his career, serving both as development and operations manager. Gregory moved back to hands-on roles in 2016 after he realized he loves the technical side of projects too much to leave it entirely to others.
Portfolio
Experience
Availability
Preferred Environment
Python 3, TensorFlow
The most amazing...
...achievement I've accomplished is filling seven AI-related patents for one of my previous employers.
Work Experience
IT Industrialization Manager
HWQ Concept
- Ran a vendor selection process based on prototype requirements.
- Developed a PLC program (Arduino/C++) for full prototype control, including data connectivity with the cloud.
- Developed a cloud-based (Azure) back end to display prototype data (PostgreSQL, FastAPI) along with the front end (Streamlit).
Machine Learning Engineer
Alight
- Developed an NLP solution for automated support tickets classification in multiple languages.
- Advised senior management on best AI use-cases for human resources software.
- Developed cloud pipeline using Azure Data Factory and Azure Functions.
Machine Learning Engineer
Continental Digital Services France
- Developed multiple predictive models to enable smarter cars, seven of which led to patent filling.
- Managed a team of six, providing technical guidance and people development.
- Initiated and led a continental-wide Kaggle-like competition, including three instances.
- Designed and delivered an AI course for beginner and intermediate-level attendees.
Business Intelligence Manager
Mars Information Services
- Managed a virtual team of 20 in charge of tier 3 support for the enterprise-wide BI reporting solutions using SAP BW, BO, and QlikView.
- Reduced running costs by 20% through right-shoring and strict implementation of ITIL processes.
- Improved bug fixes and CIPs time to market by 10% year on year.
Experience
Relaxed Lasso
https://github.com/GregVial/RelaxedLassoI implemented the paper in Python in a sci-kit-learn-compliant fashion.
Relaxed Lasso is an improvement over the standard Lasso regularizer for linear regression. It lets you control the number of variables retained, and the amount of regularization applied using two separate hyperparameters, leading to sparser models rather than classical Lasso while achieving equal or lower errors.
Predicting the Most Probable Route of a Vehicle Patent
https://worldwide.espacenet.com/publicationDetails/biblio?II=13&ND=3&adjacent=true&locale=fr_EP&FT=D&date=20200326&CC=WO&NR=2020058234A1&KC=A1I was the sole inventor of the method, and I also developed an implementation that used Python and TensorFlow.
The model was then made accessible through an API (Flask based), wrapped into a Docker container, and exposed through Azure Web App. It later served a fleet of approximately 50 demo vehicles.
The project led to a patent filing; see attached link.
Real-time Water Consumption Tracker
Electric Machine Optimization
Based on an existing machine design, a set of rules that tie together all degrees of freedom, and expert software that computes several target features for a design, I used several evolutionary strategies to explore the parameter space and come up with a design that beats the human experts, hence creating superior electric machines.
Anomaly Detection Based on Vibration
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20220602&CC=WO&NR=2022112920A1&KC=A1The first phase of the project consisted of data capture. We equipped a car with multiple sensors and then performed various drives with defects applied to the car, like low tire pressure, parallelism issues, etc.
I then analyzed the vibration data of each run and compared a standard car (no defect) with the various defects applied.
Using multiple machine learning techniques, I developed a data pipeline that included data pre-processing and a machine learning model that detected various defaults with high accuracy.
The project led to patent filing; see the link.
Skillset
Libraries/APIs
NumPy, Pandas, Matplotlib, TensorFlow, Scikit-learn, PySpark
Paradigms
Data Science, ITIL
Other
Machine Learning, Deep Learning, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNNs), Linear Regression, IT Project Management, Neural Networks, Artificial Intelligence (AI), Optimization, Interviewing, Software Engineering, Azure Data Factory, Evolutionary Algorithms, Arduino IDE, PLC, Technical Hiring, ESP32
Languages
Python 3, Python, SQL, C++
Platforms
Arduino, Azure Functions, Docker, QlikView, Amazon Web Services (AWS), Azure
Storage
PostgreSQL
Education
Master's Degree in Software Engineering
National University of Ireland - Maynooth, Ireland
Master's Degree in Software Engineering
Telecom Nancy - Nancy, France
Certifications
Project Management Professional (PMP)
PMI
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