Julian Villella
Canada
Summary
🤩
RockstarJulian Villella is a seasoned software and machine learning engineer with 12 years of experience building production-grade systems across robotics, autonomous driving, and mobile platforms. He led ML and robotics teams at Kindred, productionized an ML-based grasping system that has sorted 40M+ items, and helped incubate Huawei's open-source SMARTS platform for multi-agent RL—work that contributed to a CoRL best systems award. Equally at home in backend systems and mobile UI, he has shipped Android and iOS features at 500px and refactored widely used libraries, demonstrating a pragmatic full-stack mindset. A founder-in-residence at Entrepreneur First, he pairs startup grit with research-driven engineering and a strong commitment to open-source and self-directed learning. Notably, his contributions to SMARTS included scenario orchestration and tooling to evaluate diverse algorithm paradigms, reflecting a knack for turning experimental research into reproducible engineering.
12 years of coding experience
7 years of employment as a software developer
English, Italian
Github Skills (23)
python10
simulator10
picasso10
image-viewer10
android-sdk10
ui-design10
android-recyclerview10
reinforcement-learning10
java10
javas10
uid10
front-end-development10
android10
recyclerview10
android-imageview10
Programming languages (15)
Github contributions (5)
500px/greedo-layout-for-android
Feb 2016 - May 2016
Full aspect ratio grid LayoutManager for Android's RecyclerView
Role in this project:
Mobile Developer (Android)
Mobile Developer (Android)Contributions:28 commits, 7 PRs, 14 pushes in 3 months
Contributions summary:Julian primarily contributed to the Android application's layout and UI components, adding and modifying files related to the sample app. They implemented a grid layout manager utilizing aspect ratios for images. The user also added image loading capabilities with the Picasso library and integrated a fixed-height feature. They further refined the application's UI design by adding spacing and fixing a minor bug with the image scaling.
recyclerviewlayoutandroid-recyclerviewandroidandroid-library
huawei-noah/SMARTS
Oct 2020 - Dec 2020
Scalable Multi-Agent RL Training School for Autonomous Driving
Role in this project:Back-end Developer
Back-end DeveloperContributions:183 reviews, 141 commits, 34 PRs in 1 month
Contributions summary:Julian primarily focused on organizing and refactoring run scenarios within the `smarts` repository, specifically modifying the `benchmark` and `evaluate` scripts. They updated the configuration files and added arguments such as paradigm, log directory and horizon to handle different algorithm paradigms and logging functionalities. The commits also include changes for integrating and evaluating different agent configurations within the autonomous driving simulator.
pytorchscalablepythonautonomousagent
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.