About the RoleWe are seeking a highly skilled 3D Computer Vision Engineer with expertise in 3D reconstruction to join our R&D team. In this role, you will design, develop, and optimize algorithms and pipelines that transform images, videos, LiDAR, and depth sensor data into accurate 3D models. Your work will directly power our next-generation 3D scanning, AR/VR, and digital twin solutions.
Key Responsibilities- Develop and implement 3D reconstruction pipelines from multi-view images, RGB-D, stereo, LiDAR, or photogrammetry data.
- Research, adapt, and optimize algorithms for SLAM, SfM (Structure from Motion), and MVS (Multi-View Stereo).
- Build robust camera calibration and sensor fusion methods for RGB, depth, and IMU data.
- Integrate mesh generation, texturing, and surface reconstruction techniques into production-ready systems.
- Collaborate with the AI, robotics, and 3D graphics teams to enhance reconstruction accuracy, speed, and scalability.
- Benchmark and evaluate algorithm performance on large-scale datasets.
- Stay updated on the latest advancements in computer vision, graphics, and 3D AI.
QualificationsRequired:
- Bachelors or Masters in Computer Vision, Computer Science, Electrical Engineering, or related field.
- 3+ years of hands-on experience in 3D reconstruction projects.
- Strong proficiency in Python and C++ for high-performance computer vision.
- Experience with OpenCV, Open3D, PCL (Point Cloud Library), or similar.
- Solid understanding of geometry, linear algebra, and optimization for 3D vision.
- Familiarity with camera calibration and pose estimation methods.
Preferred:
- PhD in a relevant field or equivalent research experience.
- Experience with Neural Radiance Fields (NeRF), Gaussian Splatting, or deep learning-based reconstruction.
- Hands-on work with 3D graphics engines (Unity, Unreal) or WebGL.
- Experience in GPU acceleration with CUDA or TensorRT.
- Background in AR/VR, robotics, or autonomous systems.
Tools & Technologies- Programming: Python, C++, CUDA
- Libraries/Frameworks: OpenCV, Open3D, PCL, PyTorch, TensorFlow, COLMAP, Meshroom
- 3D Data Formats: OBJ, PLY, GLTF, USDZ
- Version Control: Git, GitHub/GitLab
- Cloud & Deployment: AWS, Docker, CI/CD pipelines
