Jingnan Shi
Co-Founder at 🤖
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolJingnan Shi is a robotics and perception software engineer with a decade of experience building robust 3D perception, localization, and control systems, currently based in Cambridge, MA. With a PhD from MIT in robotics, Jingnan has driven research and production work spanning visual-inertial odometry, point-cloud registration, and robust optimization—contributing core algorithms to influential open-source projects like TEASER++ and GTSAM. Their background blends hands-on field systems (indoor localization for Bobcat vehicles, AUV tracking) with deep algorithmic work (GNC/TLS optimizer improvements and solver implementations). Jingnan is a practical coder who focuses on maintainability and performance—refactoring VIO front- and back-ends, tightening logging, and hardening outlier handling. Now co-founding a robotics venture, they pair academic rigor with product-minded prototyping to move research into real-world autonomy. An understated strength is their attention to numerical robustness and convergence behavior, evident across both research and widely used open-source libraries.
10 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Massachusetts Institute of TechnologyShanghai World Foreign Language AcademyBachelor of Science (B.S.), Engineering, Bachelor of Science (B.S.), Engineering at Harvey Mudd College
Github Skills (20)
algorithm10
algorithms10
c-language10
gtsam10
data-structure10
parameter-estimation10
eigen10
state-space10
estimate10
data-structures10
nonlinear-optimization10
cprogramming-language10
point-cloud10
slam10
optimization10
Programming languages (9)
Github contributions (5)
MIT-SPARK/TEASER-plusplus
Jun 2019 - Oct 2022
A fast and robust point cloud registration library
Role in this project:
Back-end Developer & Algorithm Engineer
Back-end Developer & Algorithm EngineerContributions:2 releases, 9 reviews, 71 commits in 3 years 4 months
Contributions summary:Jingnan primarily worked on the TEASER++ library, a point cloud registration system. Their contributions involved implementing and refining core algorithms within the `registration.h` and `registration.cc` files, which included outlier detection and various solver methods. The user updated and improved example files and documentation. The user's work also extended to fixing size-related errors and updating the Cmake files.
roboticspythonpoint-cloudspoint-cloud-registrationoptimization
borglab/gtsam
Dec 2020 - Jan 2021
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:Back-end Developer
Back-end DeveloperContributions:11 reviews, 30 commits, 13 pushes in 1 month
Contributions summary:Jingnan primarily focused on implementing and refining the GNC (Graduated Non-Convexity) optimizer within the GTSAM library. Their work involved adding and modifying the TLS (Truncated Least-squares) loss function, including mu initialization, update, and convergence checks. They also made improvements and fixes to the overall GNC algorithm, including the calculation of weights, and wrote associated unit tests.
smoothingsparsec-plus-plushierarchicalpattern-recognition
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.