Job Description / Duties:
- Design and implement accurate 3D reconstruction pipelines from multi-modal data sources (e.g., images, LiDAR, or similar sensors).
- Build robust algorithms to automatically map and measure elements in 3D models and 2D representations.
- Research, implement, and optimize geo-positioning techniques to achieve sub-centimeter accuracy, leveraging RTK, SiReNT, LiDAR, visual markers, and hybrid approaches.
- Develop and deploy image and 3D segmentation models for real-world applications, ensuring robustness and efficiency.
- Write clear, modular, and optimized Python code to support research, prototyping, and production deployment.
- Develop software and hardware solutions for autonomous operations on ground robots and drones, including navigation in GPS-denied environments.
- Collaborate with a multidisciplinary team to translate research outcomes into practical solutions.Conduct field trials to validate algorithms and hardware performance.
Work experience/Skills required:
- PhD or Master's degree in Computer Science, Robotics, Electrical Engineering, or related field.
- Strong expertise in 3D reconstruction (photogrammetry, LiDAR, multi-view geometry, or related techniques) and 3D analysis.
- Demonstrated experience with geo-positioning technologies (e.g., RTK-GPS, SiReNT, LiDAR-based localization, visual fiducials/markers).
- Hands-on experience developing image and 3D segmentation models (deep learning, classical CV, or hybrid approaches).
- Proficiency in Python with strong software engineering practices (clean code, testing, documentation).
- Practical expertise with ground robots or UAVs (drones), including control, planning, and navigation in GPS-denied scenarios.
Preferred:
- Familiarity with SLAM frameworks, multi-sensor fusion, or VIO (Visual-Inertial Odometry).
- Experience deploying algorithms on embedded systems or edge-compute platforms.
- Experience with ROS/ROS2, C++, or GPU acceleration (CUDA, TensorRT).
