Carl Folkestad

Staff Machine Learning Engineer, Autonomy at Rivian

Los Angeles Metropolitan Area United States
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
🎓
Top School
Carl Folkestad is a Staff Machine Learning Engineer specializing in autonomy with 9 years of experience applying deep learning, reinforcement learning, and control theory to real-world robotic and vehicle systems. He holds a PhD in Control and Dynamical Systems from Caltech where he developed novel Koopman-based learning and safety-critical control methods that led to multiple ICRA/ACC publications. At Cruise he advanced behavior and trajectory selection models for real-time planning, and he now builds end-to-end driving models at Rivian, bridging research-grade theory with production autonomy stacks. Known for combining physics-informed approaches with data-driven learning, he has a track record of improving computational efficiency and safety in learned dynamics and control. Based in Los Angeles, he brings both academic rigor and hands-on systems engineering to large-scale autonomy challenges.
code9 years of coding experience
job8 years of employment as a software developer
bookMechanical Engineering, Mechanical Engineering at Massachusetts Institute of Technology
bookCalifornia Institute of Technology
bookNorwegian University of Science and Technology
languagesEnglish
github-logo-circle

Github Skills (8)

nonlinear10
state-space10
decomposition10
dynamical-systems9
pytorch7
machine-learning7
deep-learning7
swarm3

Programming languages (3)

CMATLABPython

Github contributions (5)

github-logo-circle
Cafolkes/koopman-cbf

Aug 2020 - Nov 2020

Contributions:56 commits, 2 PRs, 9 pushes in 3 months
Cafolkes/keedmd

Sep 2019 - Apr 2020

Repository for construction of Koopman eigenfunctions for unknown dynamical systems and identification of a lifted state-space model using Koopman Eigenfunction Extended Dynamic Mode Decomposition (KEEDMD).
Contributions:176 commits, 15 PRs, 18 pushes in 7 months
decompositionextendeddynamical-systemsunknownkoopman
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
Carl Folkestad - Staff Machine Learning Engineer, Autonomy at Rivian