As a SLAM Engineer at Omakase Robotics, you will own the localization, mapping, and state estimation systems that enable our robots to navigate hospitals, hotels, and retail environments — not just flat warehouse floors. This is a harder problem than what most SLAM engineers work on, and the impact is immediate: our robots are already in real environments and the systems you build will be deployed quickly.
Tech Stack
- Languages: C++, Python
- Frameworks: ROS/ROS2, PCL, OpenCV, Eigen, Ceres / g2o
- Tools: Linux, Docker, Git, NVIDIA CUDA (preferred)
Who Will Thrive Here
- Thrive in an early-stage startup where you help define how things work
- Want direct, hands-on access to real robots — a level of freedom rare at larger companies
- Move fast, iterate quickly, and care about shipping things that work in the field
- Excited about Japan’s first robotics OS platform and its real-world deployments (hospital, Tsukuba PoC)
Responsibilities
- Develop, evaluate, and deploy robust 2D/3D SLAM and state-estimation algorithms for real-world service environments
- Design and implement sensor fusion algorithms (EKF/UKF, graph-based optimization) integrating LiDAR, cameras, IMUs, and GNSS
- Implement and optimize path planning algorithms (Hybrid A*, TEB, DWA) for dynamic indoor environments
- Optimize algorithms for real-time performance on edge computing platforms and SoCs
- Develop online/offline sensor calibration toolchains
- Integrate SLAM into the full-stack autonomous software framework with perception, control, and simulation teams
- Apply latest research (NeRF, 3D Gaussian Splatting) to production mapping challenges
Requirements
- Master’s or PhD (or equivalent professional experience) in Robotics, CS, or Computer Engineering
- 3+ years of professional or strong academic experience in 2D/3D SLAM, Visual Odometry (VO), or VIO
- Production-level C++ (C++11/14/17) and solid Python skills
- Strong mathematical foundation: 3D geometry, linear algebra, coordinate transformations, non-linear optimization (Ceres, g2o)
- Hands-on experience with ROS/ROS2 in Linux development environments
- Experience processing real sensor data: 3D LiDAR, depth/RGB cameras, IMUs
Nice to haves
While not specifically required, tell us if you have any of the following.
- Experience with autonomous driving frameworks (Autoware, Apollo) — Autoware contributors especially welcome
- Point cloud processing with PCL or Open3D
- GPU optimization (CUDA) or Edge AI deployment (NVIDIA Jetson/Orin)
- Track record of deploying algorithms on physical robots or vehicles (Sim-to-Real)
- Experience with dynamic path planning (Hybrid A*, TEB, DWA)
- Docker + Git + CI/CD workflow experience
