Roberto N.
Machine Learning Engineer
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.
Hovedekspertise
Data Science10 år
Machine Learning4 år
Data Analytics8 årErfaring5
Machine Learning Engineer
- 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.
HTML
FlaskData Science
NumPy
Pandas
Data Scientist
- Developed Proof of Concept (PoC) models using the Huawei Cloud Platform for customers
MicroservicesData ScienceNumPy
OpenCVPandas
Machine Learning Engineer
- 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.
Operational ManagementMicroservices
PrototypingData ScienceNumPyData Scientist
- 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.
Data Science
Scikit-learn
ClusteringDeveloper
- 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.
Eclipse
TestNGIngeniørmæssig fremragendehed
Alle Machine Learning Engineerer, der har ansøgt til Proxify, får en score fra 0 til 300 på teknisk dygtighed, en af de fem parametre, vi evaluerer. Denne score afspejler kun teknisk dygtighed baseret på interviews, hjemmeopgaver, live kodningssessioner og/eller vurderinger af præstationer på jobbet. Kurven viser, hvordan alle evaluerede Machine Learning Engineerer er fordelt over dette interval, hvor vores acceptgrænse for denne parameter ligger, og hvor Roberto står.
Score 196 · Top 8% of engineers
Uddannelse
Stop med at søge.
Bliv matchet hurtigere.
Tal med en ekspert og få skræddersyede matches fra vores netværk på kun 2 dage.
Få adgang til over 6.000+ eksperter
Få matchet med en udvikler på gennemsnitligt 2 dage
Ansæt hurtigt og nemt med 94 % matchsuccess