Roger is available for hire

Roger Pros Rius

Verified Expert in Engineering

Machine Learning Developer

Location

Barcelona, Spain

Toptal Member Since

December 13, 2021

Roger is a data scientist and mathematics engineer with over five years of experience. He has a passion for detecting and solving real-world situations using state-of-the-art analytics, from the definition of the idea to the implementation of the solution. He has worked on different challenges, such as demand forecasting, key levers identification, and industrial process optimization. Roger's academic background is in applied mathematics and statistics with strong coding skills in Python and R.

Time Series Clustering Machine Learning Python 3 R Python SQL Data Visualization Deep Learning Computer Vision Artificial Intelligence (AI)Deep Neural Networks Natural Language Processing (NLP)PySpark Visual Studio Code (VS Code)Explainable AI

Portfolio

PepsiCo

Data Science, Explainable Artificial Intelligence (XAI), Python 3...

Avatar Cognition

Python, Python 3, Visual Studio Code (VS Code), Data Science, Machine Learning...

Boston Consulting Group (formerly Kernel Analytics)

Data Science, Consulting, Python 3, Visual Studio Code (VS Code), R...

Experience

R - 5 years Explainable Artificial Intelligence (XAI) - 5 years Statistics - 5 years Python - 5 years Operations Research - 4 years Machine Learning - 4 years Deep Learning - 3 years

Availability

Part-time

Preferred Environment

Python 3, R, Data Science, Machine Learning, Optimization

The most amazing...

...project I've developed is a tool to infer chemical formulas and their properties, consisting of optimization and a classification module.

Work Experience

Senior Data Scientist - Global

2021 - 2022

PepsiCo

Contributed to the digitalization of the company by developing AI models and insights.
Worked on the explainability component of the tools developed.
Engaged with business units and external consultants to tailor the machine learning solutions to the business needs.

Technologies: Data Science, Explainable Artificial Intelligence (XAI), Python 3, Visual Studio Code (VS Code), Machine Learning, Optimization, Statistics, Artificial Intelligence (AI), Scikit-learn

Startup Data Scientist

2020 - 2021

Avatar Cognition

Performed a data scientist role providing support to the research of an artificial general intelligence (AGI) algorithm.
Managed the Python wrapper package for the algorithm.
Researched and designed multiple benchmarks to test the AGI capabilities of the algorithm.
Developed prototypes and tested the AGI ideas and challenges.

Technologies: Python, Python 3, Visual Studio Code (VS Code), Data Science, Machine Learning, Optimization, Explainable Artificial Intelligence (XAI), Deep Learning, Statistics, Artificial Intelligence (AI), Data Visualization, Scikit-learn

Data Scientist - Consultant

2017 - 2020

Boston Consulting Group (formerly Kernel Analytics)

Identified the areas of analytics development in clients' settings and turned them into projects.
Modeled data science and optimization solutions to fix the needs of the project.
Implemented the solutions using highly reusable code.
Aided in commercial proposals and in‐house as well as trained and mentored.

Technologies: Data Science, Consulting, Python 3, Visual Studio Code (VS Code), R, Machine Learning, Optimization, Explainable Artificial Intelligence (XAI), Deep Learning, Statistics, Artificial Intelligence (AI), Data Visualization, Scikit-learn

Research Engineer

2016 - 2017

Applus+ IDIADA

Reviewed the state-of-the-art methodology in autonomous driving and implemented multiple versions of a lane-centering algorithm.
Supported mathematical modeling for multiple automotive projects.
Deployed the code in simulation engines such as PreScan.

Technologies: Python, Neural Networks, Deep Neural Networks, Computer Vision, Time Series, Artificial Intelligence (AI), Data Science, Computer Vision Algorithms, Image Processing, Optimization, Operations Research, Stochastic Modeling, Machine Learning, Scikit-learn

Experience

Chemical Formula Optimization

I built an algorithm to optimize and classify the formula inferred from a gas chromatography-mass spectrometry (GCMS) analysis while incorporating expert and business constraints.

Algorithms:
MIP modeling, random forest, and gradient boosting.

Steelmaking Process Modeling

I performed an exploration of the steel‐making process to detect and identify key levers and areas of improvement. I managed this data science exploration, working alongside business experts.

Algorithms:
SHAP values and gradient boosting.

Media Demand Forecasting

I headed the development of an automated daily demand forecasting and distribution tool with more than 2,000 sale points, including strong seasonalities and strict business rules and metrics.

Algorithms:
ARIMA models, kernel density estimation (KDE), Fourier expansion, gradient boosting, and random forest.

Lane Centering Algorithm

I reviewed the state-of-the-art methodology in autonomous driving and the implementation of multiple versions of a lane-centering algorithm.

Algorithms:
Recurrent neural networks (LSTM), convolutional neural networks, PID controllers, and model predictive control (MPC).

Consumer Products Supply Forecasting

A machine learning forecasting tool capable of creating forecasts for thousands of time series of products and locations incorporating cross-learning between products and external drivers. I was part of the team from the start of the PoC to the production-ready tool. My main tasks involved modeling, feature engineering, and developing the explainability of the model.

New AI Algorithm Research

Acted as part of a team researching a new bio-inspired AI algorithm. I was in charge of the Python wrapper for the core algorithm and of the application of the algorithm in real use cases and benchmarks. I also provided additional support in preparing documentation material for startup funding.

University Teaching Assistant

Taught multiple modules that were part of the data science master's degree.
Managed and mentored a class of 50+ students doing their master's thesis.
Collaborated as a member of the master evaluation committee with multiple projects.

Education

2016 - 2017

Master's Degree in Industrial and Applied Mathematics

ENSIMAG - Grenoble, France

2012 - 2016

Bachelor's Degree in Statistics and Operations Reseach

Universitat Politecnica de Catalunya (UPC) - Barcelona, Spain

Skills

Libraries/APIs

Scikit-learn, PySpark

Languages

Python 3, R, Python, SQL

Paradigms

Data Science

Platforms

Jupyter Notebook, Visual Studio Code (VS Code)

Other

Machine Learning, Optimization, Explainable Artificial Intelligence (XAI), Operations Research, Statistics, Forecasting, Time Series, Regression, Ridge Regression, Clustering, Classification, Artificial Intelligence (AI), Consulting, Deep Learning, Neural Networks, Deep Neural Networks, Computer Vision, Natural Language Processing (NLP), Data Visualization, GPT, Generative Pre-trained Transformers (GPT), University Teaching, Image Processing, Gradient Boosting, Fourier Analysis, Linear Regression, ARIMA Models, Computer Vision Algorithms, Stochastic Modeling

Collaboration That Works

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

Discuss your requirements and refine your scope in a call with a Toptal domain expert.

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring