João A. Leite

Applied Scientist at microsoft

Brasil, Brazil
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
João Leite is a Research Associate and PhD candidate in Computer Science at The University of Sheffield with eight years of experience building NLP and data-driven products. He has applied research to production at scale—developing a query expansion system and intent-prediction models for PicPay’s search engine used by millions—and has deep experience across the ML pipeline from web scraping to annotation, NER, sentiment and taxonomy building. At Sheffield he combines teaching and research, creating lab materials and assessment for text processing while driving doctoral research. Comfortable moving models from prototypes into A/B-tested features, he blends rigorous academic methods with product-focused engineering. Colleagues describe him as someone who bridges careful experimental design with practical deployment, often surfacing insights from noisy user-query data that aren’t obvious from aggregate metrics alone.
code8 years of coding experience
github-logo-circle

Github Skills (87)

python10
datasets10
huggingface10
deep-learning10
speech10
gpu10
cython10
multimodal10
sentiment-analysis10
audio10
ai10
computer-vision10
transformer10
nlp10
artificial-intelligence10

Programming languages (3)

C++Jupyter NotebookPython

Github contributions (5)

github-logo-circle
A simple tweet collector wrapper built on top of tweepy and optionally integrated with Google Drive. It will collect all the tweet, user, media and location fields and dump it to a json file.
Contributions:3 releases, 33 commits, 4 PRs in 3 months
tweepydata-collectionpythontwitter
joaoaleite/ToLD-Br

Oct 2020 - Jul 2021

[AACL 2020] Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis
Contributions:9 commits, 20 pushes, 2 branches in 9 months
language-detectionnatural-language-processingbertautomltoxic-comment-classification
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial