Guilherme is available for hire
Hire GuilhermeGuilherme de Oliveira da Costa Marques
Verified Expert in Engineering
Software Developer
Florianópolis - State of Santa Catarina, Brazil
Toptal member since March 15, 2016
Bio
Guilherme has studied artificial intelligence, focusing on natural language processing and data mining. Some of his work includes a recommender system prototype, low-level C applications for hardware diagnostics, and the development of a novel PaaS solution for mobile app development. Guilherme is most experienced in Python and Node.js
Portfolio
Loadsmart
React, TypeScript, JavaScript, Agile, CircleCI, Python, Django...
Loadsmart
Python, Django, Django REST Framework, PostgreSQL, Amazon Web Services (AWS)...
Loadsmart
Python, Django, Django REST Framework, Kubernetes, Terraform...
Experience
- Python - 8 years
- REST - 6 years
- Django - 4 years
- Amazon Web Services (AWS) - 4 years
- PostgreSQL - 4 years
- React - 2 years
- TypeScript - 2 years
- Node.js - 2 years
Availability
Part-time
Preferred Environment
Git
The most amazing...
...code I've written employs text mining on text to answer multiple-answer questions using Python's NLTK and Stanford NLP suite.
Work Experience
Senior Full-stack Engineer
2022 - 2023
Loadsmart
- Learned front-end development fundamentals and best practices and got acquainted with TypeScript and React while working on projects relevant to the squad.
- Performed a full reimplementation of a legacy web interface used by internal clients, employing the new design elements and frameworks adopted by the company.
- Implemented new ML system features and integrations, creating well-designed elements to bring ML information from the back end to the users.
Technologies: React, TypeScript, JavaScript, Agile, CircleCI, Python, Django, Django REST Framework, Terraform, Kubernetes, Amazon Web Services (AWS), REST
Senior Back-end Engineer | Tech Lead
2020 - 2022
Loadsmart
- Designed, implemented, and maintained a low-overhead stack responsible for training and serving ML models.
- Decommissioned a legacy ML system, replacing it with a novel implementation.
- Mentored less experienced coworkers, guiding them in improving their back-end expertise and project leadership skills.
Technologies: Python, Django, Django REST Framework, PostgreSQL, Amazon Web Services (AWS), Kubernetes, Terraform, REST, CircleCI, Agile
Back-end Engineer
2019 - 2020
Loadsmart
- Developed and maintained a simple machine learning recommender system to improve carrier experience in the platform.
- Implemented, integrated, and maintained a K-armed bandit-based system for margin suggestion.
- Debugged and maintained a legacy ML system, updating it as much as possible to meet the company standards.
Technologies: Python, Django, Django REST Framework, Kubernetes, Terraform, Amazon Web Services (AWS), REST, Agile, CircleCI
Software Engineer
2018 - 2019
Deeploop
- Maintained a Python and Twisted back end and Node.js middleware.
- Implemented new RESTful APIs in the back end and middleware.
- Integrated the back end with 3rd-party services such as Salesforce, HubSpot, and mailing services.
- Implemented reports and ETLs by leveraging MongoDB's pipeline features.
Technologies: Python, Node.js, MongoDB, Amazon Web Services (AWS), REST, Salesforce, Twisted
Back-End Developer
2015 - 2015
Carbono.io
- Worked on the design of a complete IDE and scalable PaaS solution for mobile app development and deployment.
- Developed an asynchronous event-based back end for code manipulation of projects created in the IDE, accessible through a Socket.IO interface.
- Planned a coherent code structure for the platform's projects, considering dependencies and code elements.
- Worked on the standardization of RESTful APIs and Socket.IO events across a microservice-structured platform.
- Helped in the improvement of code quality through consistent styling and the development of unit tests aiming at complete code coverage.
Technologies: Node.js, REST
Software Development Analyst
2015 - 2015
FIT - Flextronics Instituto de Tecnologia
- Worked on a hardware diagnostics application written on UEFI.
- Improved a UEFI application's USB diagnostics to support USB 3.0.
- Developed new USB diagnostics for peripheral verification and bus quality check.
- Performed bug fixes on the UEFI application's CPU and video diagnostics.
- Developed application structure improvements, including a batch execution of tests.
Technologies: C
Software Engineer
2013 - 2015
CESAR - Centro de Estudos e Sistemas Avançados do Recife
- Created a lightweight web-based heatmap tool for user interaction visualization.
- Developed a distributed recommender system based on graph data modeling using the TinkerPop suite through Aurelius Titan.
- Developed scripts for batch preprocessing of data collected by Google Analytics.
- Prototyped a recommender system based on Apache Mahout.
- Performed comparative benchmarks and performance and usability tests on e-reader platforms.
Technologies: Python
Experience
Combining Text Mining Techniques for QA4MRE 2013
http://ceur-ws.org/Vol-1179/CLEF2013wn-QA4MRE-deOliveiraDaCostaMarquesEt2013.pdfPaper describing participation in 2013's Question Answering for Machine Reading Evaluation (QA4MRE) competition. Briefly describes the work performed during MSc in Artificial Intelligence. Employed techniques that vary from simple text preprocessing and removal of formatting errors to more complex algorithms for coreference resolution. The described system got 2nd place in the competition.
(Game in Ten Days Challenge) Colorful People Quest - Curse of the Red Mage
Cooperative dungeon-crawler-ish game prototype, with procedural mazes as levels. Created with a friend for a Game in Ten Days challenge. Coded in JavaScript with Phaser.io. I was responsible for maze generation, tile lighting algorithm based on graph search, and visual adjustments. It was the first game I worked on, and even with the reduced time we were able to achieve pleasing results.
Didatic Implementation of Classic Graph Algorithms
https://github.com/guiocm/classical-graphsClassic graph algorithms implemented in Python, used as teaching material during extension classes at Universidade Federal de São Carlos, Campus Sorocaba. All code examples are clean and elegantly implemented, and were considered extremely legible by the students.
Education
2009 - 2014
Bachelor's of Science Degree in Computer Science
Federal University of São Carlos - Sorocaba, Brazil
Skills
Libraries/APIs
Node.js, React
Tools
Git, Terraform, CircleCI
Languages
Python, JavaScript, C, TypeScript
Frameworks
Django, Django REST Framework, Twisted
Paradigms
Unit Testing, REST, Agile
Platforms
Amazon Web Services (AWS), Kubernetes, Salesforce
Storage
Redis, MongoDB, PostgreSQL
Other
Machine Learning, Natural Language Processing (NLP)
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.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
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