Visual SLAM Algorithm Engineer
On-siteTokyo, Tokyo, Japan
Job Summary
Develop tightly-coupled visual-inertial-odometry fusion systems for autonomous truck operation, implementing online calibration modules to estimate camera-IMU extrinsics, time offsets, and IMU bias in real-time. Build globally consistent sparse or semi-dense maps using visual inputs and LiDAR assistance, integrating Gaussian-SLAM frameworks to combine radiance-field mapping with pose-graph optimization. Port dense matrix operations and foundation model inference to NVIDIA CUDA and TensorRT, optimizing differentiable Gaussian rasterisation kernels to achieve ≥30 Hz frame rates. Address coupling stability between calibration and localization through observability analysis and parameter-freezing strategies.
Required Qualifications
- Master's degree or higher in Robotics, Computer Vision, Automation, or a related field
- ≥3 years of hands-on experience in SLAM or VIO with real-world product deployment
- Deep understanding of SLAM/VIO core concepts
- Mastery of source-level principles of VINS-Mono, especially initialization, online extrinsic calibration, and marginalisation strategies
- Mastery of IMU fusion, map reuse mechanisms, and multi-map merging in ORB-SLAM3
- Proficient in CUDA C/C++ with solid knowledge of memory models, warp divergence, and bank conflicts
- Demonstrated CUDA optimisation of at least one of: sparse matrix operations, graph optimisation solvers, feature matching, optical flow, or 3DGS rasterisation kernels
Desired Qualifications
- Expertise in observability analysis (e.g., Fisher information matrix) and hands-on experience with IMU-Camera extrinsic/time-delay calibration
- Familiarity with Gaussian-Splatting; experience with Gaussian-SLAM or similar real-time radiance-field SLAM
- Experience with MASt3R, VGGT and ability to inject their depth/geometry outputs as priors into traditional VIO optimisation
- Proficient in C++ (≥C++17) and Python
- Experienced with an optimisation library such as Ceres, g2o, or GTSAM
- Familiar with ROS/ROS2 and real-hardware deployment (drones, robots, AR glasses)
- Publications in ICRA, IROS, CVPR, or related venues on online calibration, observability analysis, or 3DGS acceleration
- Successful engineering solutions that mitigated calibration drift in long-duration robot operations
- Experience with multi-IMU redundant systems for online extrinsic calibration
- Open-source contributions on GitHub related to CUDA-accelerated SLAM or 3DGS
- Familiarity with cuSOLVER / cuSPARSE for back-end optimisation acceleration
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.