Afonso is available for hire

Afonso de Sá Delgado Neto

Verified Expert in Engineering

Back-end Developer

Location

Recife - State of Pernambuco, Brazil

Toptal Member Since

April 26, 2021

Afonso is a software engineer with 3+ years of experience developing end-to-end back-end services. With solid skills in cryptography and machine learning, he has also performed complex data analysis in big data scenarios. Afonso brings a challenge-driven mindset, strong focus, and curiosity to solving real-world problems, using the best practices available.

Cryptography Jupyter Python Java Algorithms Machine Learning Statistics Embedded Systems Linux Git Visual Studio Code (VS Code)PyCharm Scala Spark JavaScript LightGBM Transfer Learning

Portfolio

Incognia Companies

Java, Scala, Spark, JavaScript, Node.js, Python, Bash, Kubernetes, Docker...

Asa Branca Rocket Design (Internship)

C++, Python, Jupyter, Linux, Arduino, Embedded Systems, Drones

Experience

Python - 3 years APIs - 2 years Machine Learning - 2 years Java - 2 years REST - 2 years Cryptography - 2 years Node.js - 2 years JavaScript - 2 years

Availability

Part-time

Preferred Environment

Linux, Visual Studio Code (VS Code), IntelliJ IDEA, PyCharm, Jupyter, Git

The most amazing...

...project I've developed is a back-end service that performs street address matching in a fully anonymized manner for 1,000 requests per second.

Work Experience

Software Engineer

2019 - 2021

Incognia Companies

Participated in the early stages of the anonymization team, engaging in R&D to align the company's products to a privacy-oriented vision.
Intensively studied state-of-the-art themes on privacy, such as probabilistic data structures, homomorphic encryption, private information retrieval, and differential privacy.
Collaborated in the development of a probabilistic data structure for analyzing data with no need to deal with the raw information of a user's location. This was used by all data analytics teams in the company.
Developed and deployed a private match service, providing address validation of users without knowing their location, which received up to 1,000 requests per second. It was written in Java using the Micronaut framework.
Assisted in the development and enhancement of the company's main product: private, continuous authentication based on a user's location. I performed data analysis and defined new algorithms and solutions.
Took part on the task force to provide insights based on geolocation data to help local Brazilian authorities deal with the COVID-19 crisis.
Developed the back end and front end of an internally deployed mobile app (in React Native) to test the company's product in a straightforward manner.
Created and deployed a machine learning model used by the company's main product to detect fraudulent mobile transactions.
Wrote study materials and conducted 30+ study groups covering abstract algebra, cryptography, machine learning, fraud detection, and MLOps.

Technologies: Java, Scala, Spark, JavaScript, Node.js, Python, Bash, Kubernetes, Docker, PostgreSQL, SQL, Jupyter, Cryptography, Differential Privacy, React, Machine Learning, TypeScript, React Native, Abstract Algebra, Algorithms, Amazon Web Services (AWS), REST, APIs, Apache Kafka, Redis, Amazon RDS, Amazon Elastic Container Registry (ECR), Amazon EC2, Amazon EKS, Amazon S3 (AWS S3), REST APIs, Microservices, LightGBM

Developer and Researcher

2017 - 2019

Asa Branca Rocket Design (Internship)

Developed a framework for interaction between an Arduino device and the V-REP simulator in order to allow the simulation of the control system of a CubeSat, using C++ and Python.
Collaborated with the drone branch team that specified hardware, mounted, and programmed the drones, using C++.
Developed the software side of a hardware test platform for tuning control parameters to improve stability of drones, using C++ and Python.

Technologies: C++, Python, Jupyter, Linux, Arduino, Embedded Systems, Drones

Experience

Neural Network for Recognizing Chess Pieces

https://ieeexplore.ieee.org/document/8921043

A neural network model that uses transfer learning to recognize chess pieces from images and recreate the entire board from a photo. This project resulted in a published article on the 2019 Symposium on Virtual Reality (SVR) website.

Privacy-oriented Data Structure: MinCodeSample

https://bit.ly/3dCjtE4

Created a privacy-oriented data structure capable of estimating histograms for large sets of data without disclosing the inner, user-related information. It uses an extension of the HyperLogLog data structure.

Education

2015 - 2021

Bachelor's Degree in Electrical Engineering

Federal University of Pernambuco (UFPE) - Recife, Brazil

Certifications

MAY 2019 - PRESENT

Deep Learning Specialization

Coursera

Skills

Languages

Python, Java, Scala, JavaScript, Bash, SQL, TypeScript, C++

Tools

Jupyter, IntelliJ IDEA, PyCharm, Git, Amazon Elastic Container Registry (ECR), Amazon EKS

Other

Cryptography, Abstract Algebra, Machine Learning, Data Structures, Statistics, Embedded Systems, Drones, Image Recognition, Algorithms, HyperLogLog, Differential Privacy, Deep Learning, Neural Networks, Data Privacy, APIs, Amazon RDS

Frameworks

Spark, React Native, LightGBM

Libraries/APIs

Node.js, Keras, React, TensorFlow, REST APIs

Platforms

Linux, Visual Studio Code (VS Code), Docker, Arduino, Kubernetes, Amazon Web Services (AWS), Apache Kafka, Amazon EC2

Storage

PostgreSQL, Redis, Amazon S3 (AWS S3)

Paradigms

REST, Microservices

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