Artificial Intelligence Engineer at Fundação Getúlio Vargas (FGV).
I am a Artificial Intelligence Engineer in the Escola de Matemática Aplicada (EMAp) at the Fundação Getúlio Vargas (FGV), my research lies at the intersection of Urban Perception, Deep Learning, and Interpretability Machine Learning. I am especially interested in building efficient, and robust models that can perform analyzing, and understanding human perception from street images with or without associated description text to improve the identification of the visual components, and main perceptual features extraction for applications in urban computing. I’m also a back-end developer very passionate about Python, Golang, and DevOps.
Fundação Getúlio Vargas (EMAp) Rio de Janeiro, Brazil
Data Scientist May 2019 - Current
My work relies in two main projects: (i) Timberflow: It is focused on detecting illegal timber operations in the Amazon Rainforest; (ii) Urban safety Perception(UrbEX): Analyse criminal data and urban perception on street images. For a better organization, teams organized Scrum ceremonies to increase developer engagement in all projects.
TimberFlow: I integrated two major Brazilian databases (Sinaflor and Sisflora) of wood-based product transportation/exportation. Using libraries like Pandas and Selenium, my work helps to automate the process of cleaning, filter, and unifying both datasets, resulting in a very simple and organized database (link to reference).
Urban Safety Perception: Analyzing street view images, we extract main features from them to map zones with criminal rate records. We use several techniques based on object segmentation (DeepLabv3+), object detection (Faster-RCNN), and GANs. As main results, we can correlate and understand why streets could be safely perceived (link to reference).
Tech stack: Python, Numpy, Pandas, Keras, Pytorch, DJando, Flask, GIT, Selenium, Flask, Scrum.
CERNICALO S.A. Lima, Peru
Web Development Engineer August 2017 - May 2018
Facultad de Ciencias Lima, Peru
Teaching Assistant August 2017 - Dec 2017
Centro de Tecnologías de Información y Comunicaciones (CTIC) Lima, Peru
Research Assistant Jan 2016 - July 2017
Universidad Católica San Pablo (UCSP) Arequipa - Peru
M.Sc. in Computer Science 2018 - 2020
Thesis: Identification and Extraction of Visual Characteristics to Understand the Urban Perception through Street Images - Slides
Supervisor: PhD. Jorge Poco Medina
Universidad Nacional de Ingeniería (UNI) Lima - Peru
B.Sc. in Computer Science 2012 - 2017
Project: Design and implementation of the core level of a transversal platform based on Fog Computing architectures - Slides
Supervisor: PhD. Manuel Castillo Cara
To know further about my research line, visit this link.
Category | Proficiency in approximate descending order from left to right |
---|---|
Programming Languages | C, C++, Go, Python, R, M (Octave/MATLAB), Javascript |
Web Technologies | HTML, CSS/SCSS, Django, VueJS, ReactJS, Flask, BeeGo, Gorilla, Node.js, Angular, Jekyll |
Databases/Storage | PostgreSQL, MySQL, MongoDB |
Data Analysis/Modeling | Keras, Pytorch, Tensorflow, Pandas, Numpy, Scikit-learn, Beautiful soup, Matplotlib, Seaborn, Scrapy |
Cloud | AWS (EC2, Route 53 Console) |
Productivity Tools | LaTeX, GIT, Jupyter |
Software Engineering | Test-Driven Development: Selenium |
Machine Learning Techniques | Clustering, classification/regression, dimensionality reduction. |
Available on request.