Juarez Da Silva Bochi is a seasoned Machine Learning Engineer and software leader with 15 years of experience building large-scale, production ML and distributed systems across companies like Google, Shopify, Grammarly and The New York Times. He has led projects that materially improved search interpretation and recommendation quality—at Shopify he headed an ML initiative that saved hundreds of millions annually—and has productionized transformer-based models and CATE/CTR pipelines using Spark and Flink. Juarez combines deep back-end engineering with practical ML delivery, proven by contributions to high-profile open-source projects such as Logstash and Flask-Admin and by enhancing an HLS m3u8 parser to handle complex playlist scenarios. Comfortable in both technical leadership and hands-on coding, he excels at reducing latency, automating marketing workflows, and ensuring robust data pipelines so models stay fresh in production. Based in New York, he pairs an M.Sc. in Computer Science with an electrical engineering background, which informs his systems-first approach to machine learning. A detail that often surprises collaborators: beyond modeling he routinely contributes low-level parser and metrics fixes in open-source infra that keep real-time systems reliable.
15 years of coding experience
17 years of employment as a software developer
Electrical Engineer, Eletronics, Telecommunications, Electrical Engineer, Eletronics, Telecommunications at Federal University of Rio Grande do Sul
Python m3u8 Parser for HTTP Live Streaming (HLS) Transmissions
Role in this project:
Back-end Developer
Contributions:27 commits, 1 issue in 2 years 4 months
Contributions summary:Juarez primarily focused on enhancing the m3u8 parser functionality. Their contributions involved parsing and extracting critical information from HLS playlists, such as chunk durations, titles, and encryption keys. They added features for handling float durations, program date time and discontinuity tags and improved the parsing of variant playlists with multiple keys, codecs and IFrame playlists. Testing was a key part of the work, with the inclusion of several test cases to validate different playlist formats.
Logstash - transport and process your logs, events, or other data
Role in this project:
Back-end Developer
Contributions:13 commits in 9 months
Contributions summary:Juarez primarily contributed to the `metrics` filter within the Logstash project. Their work involved adding new configuration options for controlling the flush and clear intervals. They also added tests for the metrics filter and addressed a key collision issue that arose when multiple instances of the filter were used. Furthermore, the user made enhancements to the rate and percentile configurations of the metric filter.
eventsstreamingloggingetl-frameworklogstash
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
Juarez Da Silva Bochi - Member Of Technical Staff at Ant