Felipe Codevilla
Staff Machine Learning Engineer at Torc Robotics
Montreal, Quebec, Canada
Summary
🤩
Rockstar🎓
Top SchoolFelipe Codevilla is a Staff Machine Learning Engineer and robotics researcher based in Montreal with 11 years of experience applying ML to real-world autonomous systems. He blends academic rigor—PhD-level research in AI and postdoctoral work at Mila—with hands-on engineering at companies like Oxbotica, Torc Robotics, and Independent Robotics, focusing on robotics, computer vision, image compression, and imitation/reinforcement learning. Felipe has contributed performance and client-side improvements to the widely used CARLA autonomous driving simulator, demonstrating practical systems skills beyond pure research. His work consistently targets grounded research that yields deployable software, often optimizing connections and robustness in simulation and autonomy stacks. Comfortable across research, backend performance engineering, and production ML, he brings a track record of turning complex perception and control ideas into reliable implementations.
11 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD Artificial Inteligence, Doctor of Philosophy - PhD Artificial Inteligence at Universitat Autònoma de BarcelonaMaster's degree National Oil Agency Schoolarship Computer Engineering, Master's degree National Oil Agency Schoolarship Computer Engineering at Universidade Federal do Rio Grande - FURGMaster's degree Computer Vision and Robotics, Master's degree Computer Vision and Robotics at Universitat de Girona
English, Spanish, Portuguese
Github Skills (11)
simulations10
simulation10
simulator10
networking10
python10
carla10
unreal9
exception-handling9
unreal-engine-49
unreal-engine-59
autonomous-driving8
Programming languages (3)
Github contributions (5)
carla-simulator/carla
Oct 2017 - Oct 2019
Open-source simulator for autonomous driving research.
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:173 commits, 26 PRs, 218 pushes in 1 year 11 months
Contributions summary:Felipe contributed significantly to the `carla-simulator/carla` repository by adding and refining the Carla Client, a core component for interacting with the simulation server. The user introduced features related to episode configuration and management. They also made performance-related improvements, specifically by enhancing connections and addressing general exception handling in the client.
deep-reinforcement-learningsimulationcarlasimulatorsimulator-source
carla-simulator/imitation-learning
Dec 2017 - Nov 2018
Repository to store conditional imitation learning based AI that runs on CARLA.
Contributions:26 commits, 4 PRs, 25 pushes in 10 months
pytorchdeep-learningconditionalcomputer-visionmachine-learning
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.