JX Mo

K-Bot is an open-source, developer-focused humanoid platform I envisioned and created as a skunkworks project at K-Scale. As Head of Product & Engineering, I recruited and led the engineering team across the full stack: RL-based whole body control with sim2real, ML training library, operating system, hardware design, and manufacturing from prototyping to production in less than 6 months — as well as product design and marketing. K-Bot is the United States' first consumer & open-source humanoid robot. In the July 2025 launch, we sold out 150+ pre-order units for USD$2M+ to developers and research labs, and delivered the first batch before the company's abrupt and unexpected shutdown.

2025

After creating the Zeroth-01, I developed the core IP and technology direction for Zeroth Bot — a $2k open-source humanoid with an open-source SDK & sim for RL/VLA training with my team. Prototypes were validated in Stanford's CS234 Reinforcement Learning course, and the public waitlist grew to 20k+. We're proud to have partnered with JoyIn, a consumer robotics company, to bring the robot to the world. Launched by JoyIn at CES and covered by CNET.

2025

Zeroth-01 is the world's smallest 3D printable and open-source end-to-end humanoid robot for $350 BoM. I created it with Kelsey and Denys — we designed and built the full stack from RL training and the operating system to hardware, and launched it. The open-source community now has 5000+ members with over 700+ stars on GitHub, used by educators, developers, and labs all over the world.

2024

As engineering project lead, we built an industrial robot visual programming, testing, and deployment platform that allowed non-programmers to construct industrial robot behavior trees through a graphical interface, allowing testing in simulation, debugging, and deployment onto real robots. We shipped features to partners and clients including Mecademic Robotics.

2024

I worked on the F1TENTH team at NTU for the autonomous racing challenge. I designed the software architecture for ROS topics, vehicle state, dynamics, and navigation. I implemented global trajectory planning and local avoidance algorithms in ROS2, integrating hardware and software for planning and controller.

NTU Singapore (2024)

I built controllers, planners, inverse/forward kinematic/dynamics algorithms, and action client/server framework from scratch with ROS1 with C++ for the Kinova Gen3 robotic arms for dynamic grasping. Controllers covered kinematics and dynamic control, redundancy resolution, force control and contacts, and grasping. Planners covered trajectory generation, potential fields, and collision detection and avoidance.

McGill University (2023)