Ignacio Avas
Machine Learning Engineer at Synquery
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolIgnacio Avas is a machine learning engineer based in New York with 12 years of software and ML experience and a Master's in Artificial Intelligence from KU Leuven. He has delivered production-grade ranking and recommendation systems—improving search NDCG by 10% at Hired and replacing rule-based recommenders with neural approaches at Tophatter—while owning ML Ops, ETL, and CI/CD for scalable deployments. Proficient across Python, PyTorch, TensorFlow, XGBoost, and PySpark, he also built dynamic GPT-driven marketplace assistants handling hundreds of conversations and implemented bias-mitigation strategies to ensure fair model behavior. His background in full-stack and front-end work (including contributions improving timeline clustering in a popular graph visualization repo) gives him a strong product-oriented perspective on ML features. Comfortable leading cross-functional efforts, he blends research outputs—coauthoring a peer-reviewed paper—with hands-on engineering to move models from prototype to production. Unexpectedly, his early career in computer graphics and long tenure across startups and enterprise teams inform a pragmatic, user-focused approach to ML system design.
12 years of coding experience
11 years of employment as a software developer
Master's degree Artificial Intelligence, Master's degree Artificial Intelligence at KU LeuvenEngineer’s Degree Computer Graphics, Engineer’s Degree Computer Graphics at Universidad de la República
Spanish, English, Italian, Portuguese, Dutch
Github Skills (4)
javascript10
user-interface10
documentation9
html7
Programming languages (10)
Github contributions (5)
almende/chap-links-library
Jul 2014 - Jul 2014
a web based visualization library for displaying graphs, networks, and timelines
Role in this project:
Front-end Developer
Front-end DeveloperContributions:9 commits, 1 PR, 1 comment in 1 day
Contributions summary:Ignacio primarily focused on enhancing the functionality and documentation of the project's timeline visualization features. Their contributions include moving options within the `Timeline` class, which improved code organization. They added documentation for the `clusterMaxItems` option and integrated new methods for cluster selection and retrieval, along with related UI updates. These changes indicate an effort to improve user interaction and control over the timeline's clustering capabilities.
visualization
igui/RPSolver
Apr 2014 - Nov 2017
Contributions:2 releases, 361 commits, 78 pushes in 3 years 8 months
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.