Erik Nelson is a Staff Software Engineer with 12 years of experience specializing in robotics, state estimation, SLAM, and 3D reconstruction, currently building vehicle calibration systems at Latitude AI. He was a founding member and technical lead for mapping and localization at Nuro and has applied computer vision for Vision Pro at Apple and long-range perception at Waymo and X. Erik combines deep academic credentials (PhD in robotics/vision from UC Berkeley and an MS from CMU) with hands-on production experience across autonomous vehicles, nuclear-contamination visualization, underwater ROVs, and archaeological cavern mapping. He contributes to foundational open-source tooling for robotics—improving test coverage and robustness in the well-known GTSAM library—reflecting a focus on correctness and long-lived infrastructure. Known for “building tools nobody asked for,” he blends mathematical rigor with pragmatic engineering to deliver safe, scalable mapping and localization systems. Based in San Francisco, he pursues ambitious 3D mapping problems that span industry and science.
12 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Robotics Computer Vision Machine Learning, Doctor of Philosophy (Ph.D.) Robotics Computer Vision Machine Learning at University of California, Berkeley
California Polytechnic State University, San Luis Obispo
Master’s Degree Robotics, Master’s Degree Robotics at Carnegie Mellon University
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
Role in this project:
QA Engineer / Test Automation Engineer
Contributions:5 commits, 3 PRs, 5 comments in 1 day
Contributions summary:Erik focused on improving the test coverage within the GTSAM library. They addressed a critical issue by fixing an infinite loop in the nonlinear optimizer. Furthermore, the user added unit tests for the attitude factor and ensured that copy and move operations are properly supported, enhancing the library's robustness. Their contributions highlight a focus on code correctness and testing.
Contributions:28 pushes, 1 branch in 7 years 9 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.