JOB ID 28253
Visual SLAM Algorithm Engineer (Online Localization & Calibration)
- メーカー, 自動車
- その他（ローカリゼーション・QA等）,IT, 製品エンジニア（ハード・ソフトウェア）
- 東京都
- 1500万円～2500万円
2024年4月に設立された日本のディープテック系スタートアップ企業。大型トラック向け自動運転システムの開発を専門とし、ドライバー不足や高齢化、物流需要の増加といった日本の物流業界が抱える課題の解決を目指している。高速道路を利用した幹線輸送に重点を置き、AIを活用した先進的な自動運転技術により、輸送の安全性と業務効率の向上、物流コストの削減を推進している。自動車メーカーや物流企業との連携を通じて、自動運転トラックの実用化と次世代の物流インフラの構築に取り組んでいる。
A Japanese deep-tech startup established in April 2024, specializing in the development of autonomous driving systems for heavy-duty trucks. The company aims to transform Japan’s logistics industry by addressing challenges such as driver shortages, an aging workforce, and increasing freight transportation demand. Focusing on autonomous highway transportation, it develops advanced AI-powered technologies designed to improve transportation safety, operational efficiency, and logistics sustainability. Through collaboration with automotive manufacturers and logistics companies, the company is working toward the commercialization of autonomous trucking solutions and the development of next-generation automated freight transportation infrastructure in Japan.
This role focuses on developing next-generation visual SLAM systems with online self-calibration capabilities. The position is responsible for solving online localization and sensor calibration during autonomous truck operation using geometric SLAM, 3D Gaussian Splatting, and vision foundation models.
募集要項
-
- 職種要約
- ・Develop tightly-coupled visual-inertial odometry fusion for real-time online localization.
・Design and implement online calibration modules for camera-IMU extrinsics, time offset, IMU bias, and scale factor estimation.
・Build globally consistent sparse/semi-dense maps using visual and LiDAR-assisted inputs.
・Integrate Gaussian-SLAM frameworks and pose graph optimization for high-fidelity mapping.
・Accelerate SLAM and depth inference pipelines using CUDA and TensorRT on NVIDIA GPUs.
・Optimize Gaussian rasterization kernels for real-time 3D Gaussian Splatting.
・Improve robustness and stability of online calibration and localization systems.
-
- 応募資格（必須）
- ・Master’s degree or higher in Robotics, Computer Vision, Automation, or related fields.
・3+ years of hands-on experience in SLAM or VIO with real-world deployment.
・Strong expertise in at least one SLAM/VIO framework such as VINS-Mono or ORB-SLAM3.
・Proficient in CUDA C/C++ optimization for SLAM-related workloads.
・Proficient in C++ (C++17 or later) and Python.
・Experience with optimization libraries such as Ceres, g2o, or GTSAM.
・Familiarity with ROS/ROS2 and real hardware deployment environments.
-
- 応募資格（優遇）
- ・Experience with online calibration and observability analysis.
・Familiarity with Gaussian-Splatting / Gaussian-SLAM / NeRF-based SLAM systems.
・Experience using foundation models such as MASt3R or VGGT.
・Publications in ICRA/IROS/CVPR related fields.
・Experience solving long-term calibration drift issues.
・Open-source contributions related to CUDA-accelerated SLAM or 3DGS.
-
- 勤務地
- 東京都
-
- 勤務スタイル
- 在宅勤務OK, フレックス勤務OK
-
- 給与
- 1500万円～2500万円
-
- こだわり条件
- 海外展開, 土日祝休み, 大手企業
Consultation
自動車・モビリティ業界における
転職やキャリア設計、
求人の選定の
ご相談を承ります。
