Roberto N.

Machine Learning Engineer

Roberto is a seasoned Machine Learning Engineer with over a decade of commercial experience spanning data science, machine learning, cloud computing, and software engineering.

Roberto specializes in end-to-end ML model deployment, natural language processing (NLP), and deep learning using Python, PyTorch, and Scikit-learn. He is also proficient with cloud platforms, particularly AWS, and has contributed to impactful projects across banking, retail, and entertainment sectors. Notably, he led digital transformation initiatives at Banco do Brasil.

With a passion for robotics and reinforcement learning, Roberto brings innovative thinking and a results-driven approach to every project he undertakes.

Principale expertise

  • Data Science 10 ans
  • Machine Learning
    Machine Learning 4 ans
  • NLP 8 ans

Autres compétences

  • Bash
    Bash 15 ans
  • HTML / CSS 15 ans
  • HTML
    HTML 15 ans
Roberto

Roberto N.

Portugal

Commencer

Expérience sélectionnée

Emploi

  • Machine Learning Engineer

    Majid Al Futtaim - 4 années

    • Developed an end-to-end Programming Optimizer AI tool.
    • ShowtimeAI integrates advanced machine learning with optimization techniques to forecast daily movie session occupancy and devise optimal schedules.
    • By efficiently addressing customer demands for movie sessions, ShowtimeAI has achieved a 13% lift in revenue.

    Les technologies:

    • Les technologies:
    • HTML HTML
    • Flask Flask
    • Data Science
    • NumPy NumPy
    • Pandas Pandas
    • PyTorch PyTorch
    • CSV
    • Command-line interface
    • Scikit-learn Scikit-learn
    • Matplotlib Matplotlib
    • Data Analytics
    • Random Forest Random Forest
    • PCA
    • Convolutional neural network Convolutional neural network
    • Recurrent neural network
    • Machine Learning Machine Learning
    • Cuda Cuda
    • SQLAlchemy SQLAlchemy
    • Streamlit Streamlit
    • VPN
    • Plotly Plotly

  • Data Scientist

    G42 - 1 an 1 mois

    • Developed Proof of Concept (PoC) models using the Huawei Cloud Platform for customers

    Les technologies:

    • Les technologies:
    • Microservices
    • Data Science
    • NumPy NumPy
    • OpenCV OpenCV
    • Pandas Pandas
    • Open source Open source
    • PyTorch PyTorch
    • SciPy SciPy
    • Scikit-learn Scikit-learn
    • Splunk Splunk
    • Matplotlib Matplotlib
    • Data Analytics
    • Random Forest Random Forest
    • Convolutional neural network Convolutional neural network
    • Recurrent neural network
    • NLP
    • Machine Learning Machine Learning
    • Computer Vision
    • Cuda Cuda
    • Plotly Plotly

  • Machine Learning Engineer

    Banco do Brasil - 2 années 1 mois

    • Created a set of machine learning templates covering various techniques such as classification, regression, time series, clustering, web scraping, and integer programming. These templates provide an end-to-end solution for machine learning engagements and significantly accelerate the development process by providing a starting point for feature engineering, model optimization, deployment scripts, and more.
    • Developed and deployed a comprehensive DevOps pipeline for machine learning models, significantly reducing deployment time from months to one week. The channel has enabled the deployment of, on average, one model per day.
    • Implemented a service with a Jupyter Lab environment with pre-installed standard libraries and seamless integration with GitLab. The service has seen significant adoption, with 400 users and over 1,000 engagements created in Q1 2021.
    • Mentored new data scientists by sharing best data science, programming, and software engineering practices. This mentorship program is initiated at the start of an engagement and concludes with model deployment. A key deliverable of this mentorship program is the solution architecture design. Areas of focus include Software Architecture, Machine Learning, and DevOps.

    Les technologies:

    • Les technologies:
    • Operational Management
    • Microservices
    • Prototyping
    • Data Science
    • NumPy NumPy
    • XGBoost XGBoost
    • Pandas Pandas
    • R (programming language) R (programming language)
    • Open source Open source
    • CSV
    • Command-line interface
    • VSCode VSCode
    • SciPy SciPy
    • Scikit-learn Scikit-learn
    • ELT
    • Matplotlib Matplotlib
    • Data Analytics
    • Random Forest Random Forest
    • SVM
    • PCA
    • Convolutional neural network Convolutional neural network
    • Recurrent neural network
    • Enterprise Architect Enterprise Architect
    • NLP
    • Machine Learning Machine Learning
    • Cuda Cuda
    • BeautifulSoup BeautifulSoup
    • SQLAlchemy SQLAlchemy
    • Swagger Swagger
    • Plotly Plotly
    • Dimensional modeling
    • Information Architecture
    • COBOL

  • Data Scientist

    Banco do Brasil - 3 années 5 mois

    • Developed a Machine Learning Model to predict the digital customers' income. The model was used to create a prioritized list for the call center, resulting in projected savings of US$ 250,000 in the first year.
    • Developed a Machine Learning Model based on a Net Promoter Score survey to discover the main aspects of detractors' experience. The results showed that an imbalance between high waiting and low queue service times was the most significant cause of dissatisfaction. The company changed the queueing policies, which solved the problem country-wide. The model is now used every year to analyze customer happiness.
    • Analyzed the customer segmentation for a new credit card app, using Clustering and Association Rule Analysis to segment and then explain the segments. The results were used to guide the development of the User's Experience (UX) Journey.

    Les technologies:

    • Les technologies:
    • Data Science
    • Scikit-learn Scikit-learn
    • Clustering

  • Developer

    Banco do Brasil - 8 années 2 mois

    • Developed an automated test framework for mainframe code, which is now part of the DevOps system, continuously testing and checking coverage over 150,000 modules.
    • Created a reservation queue ticket mobile app that allowed premium customers to find the nearest branch and reserve a position on its cashier queue. This app, created in 2015, is still being used nationwide. It was specifically developed the nearest branch search feature using geolocation data.
    • Analyzed performance issues of network equipment for 30 branch offices by evaluating eight variables and using statistical tests. They identified that specific equipment was incompatible with the technology of certain telephone operators, later confirmed by network specialists.

    Les technologies:

    • Les technologies:
    • Eclipse Eclipse
    • TestNG TestNG
    • COBOL

Éducation

  • Maîtrise ès sciencesComputer Science

    Universidade de Brasília · 2016 - 2018

  • License ès sciencesMathematics

    Universidade de Brasília · 2000 - 2005

  • License ès sciencesMathematics

    Universidade de Brasília · 2000 - 2005

Trouvez votre prochain développeur en quelques jours et non sur plusieurs mois

Dans un court appel de 25 minutes, nous voulons:

  • Comprendre vos besoins en développement
  • Vous expliquez comment nous allons vous mettre en relation avec le développeur le mieux qualifié pour votre projet, sélectionné avec soin
  • Vous indiquez nos prochaines démarches afin de vous trouver le meilleur développeur, souvent en moins d'une semaine

Contactez-nous

Le premier développeur commence en quelques jours. Pas de discours de vente agressif.