Martin Bokeloh
Staff Software Engineer at Intrinsic
Germany
Summary
🤩
Rockstar🎓
Top SchoolMartin Bokeloh is a Staff Software Engineer based in Germany with over seven years of experience building robust robotics and SLAM systems at companies including Intrinsic, X (the Moonshot Factory), and Google. He combines deep academic training—a PhD-level background from the Max Planck Institute and postdoctoral research—with hands-on engineering, shipping back-end algorithms and test automation for real-time 2D/3D mapping (notably contributions to the widely used Cartographer SLAM project). Martin specializes in pose graph optimization, implementing 3D relative pose and rotation constraints and integrating them with Ceres Solver, while also driving test design and serialization validation to ensure correctness. At Intrinsic he has progressed into staff-level responsibilities, balancing low-level numerical rigor with production-quality software practices. Colleagues can expect a pragmatic problem solver who moves fluidly between research-grade algorithm design and scalable, testable engineering.
7 years of coding experience
11 years of employment as a software developer
PhD, Computer Science, PhD, Computer Science at Max Planck Institut für Informatik
Github Skills (11)
mappings10
ceres-solver10
localization10
robotics10
c-language10
cprogramming-language10
testing10
geom9
3d9
geometry9
slam9
Programming languages (4)
Github contributions (5)
cartographer-project/cartographer
Jul 2018 - Jul 2018
Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:7 commits, 14 PRs, 7 pushes in 5 days
Contributions summary:Martin primarily contributed to the Cartographer project by adding and modifying cost functions and constraints within the pose graph optimization framework. They implemented relative pose and rotation constraints in 3D, which involved defining cost functions and integrating them into the optimization process using Ceres Solver. Furthermore, the user wrote and refactored tests for the newly implemented features, ensuring the correctness and functionality of the added components. This includes the creation of test cases, serialization tests, and validation of constraint behavior.
roboticsplatformsself-drivingcartographermapping
mbokeloh/cartographer
Jul 2018 - Jul 2018
Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.
Contributions:26 pushes, 13 branches in 5 days
platformscartographermappingsensorsimultaneous
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.