Job Description

About the Role: We are seeking a skilled Geospatial Vision Engineer with 2+ years of experience to join our team. You will be responsible for developing and optimizing advanced vision algorithms, focusing on 3D depth estimation, geospatial analysis, multi-sensor object detection, and drone-based 3D vision. If you are passionate about AI, sensor fusion, and working with LiDAR, point cloud, hyperspectral cameras, and drone imaging, we would love to hear from you! Required Qualifications: Education: Bachelors or Masters degree in Computer Science, Electrical Engineering, Remote Sensing, or a related field. Technical Skills: Strong programming skills in Python and C++. Experience with OpenCV, TensorFlow, PyTorch, Keras, and Scikit-learn. Proficiency in deep learning architectures like CNNs, RNNs, and Vision Transformers. Hands-on experience with object detection and segmentation models such as YOLO, Faster R-CNN, and SSD. Proficiency in 3D libraries such as Open3D, PCL (Point Cloud Library), PDAL, and Meshlab. Expertise in geospatial vision, 3D depth estimation, multi-sensor fusion, and drone-based 3D vision. Experience working with LiDAR, point cloud, hyperspectral cameras, satellite imagery, and drone-mounted sensors. Familiarity with cloud computing platforms (AWS, Google Cloud). Understanding of MLOps tools (Docker, Kubernetes, ONNX, TensorRT, or OpenVINO). Soft Skills: Strong analytical and problem-solving abilities. Ability to work independently and within a team. Key Responsibilities: Develop and Optimize Geospatial Vision Algorithms: Design,implement, and optimize computer vision and deep learning models for 3D depth estimation, geospatial analysis, and 3D object detection. Implement and fine-tune object detection models for multi-sensor fusion, integrating LiDAR, hyperspectral imaging, point cloud data, and drone-based 3D vision. Machine Learning & Sensor Fusion Implementation: Train, fine-tune, and deploy deep learning models using TensorFlow, PyTorch, OpenCV, and Scikit-learn. Work with CNNs, transformers, and self-supervised learning techniques for geospatial applications. Optimize models for edge computing and real-time processing in autonomous systems and drones. Data Processing & Model Training: Experience with 3D Annotation tools for 3D data preparation Process and augment large-scale 3D datasets including LiDAR, satellite imagery, drone imaging, and hyperspectral and depth estimation data. Optimize model performance for real-time applications on cloud and embedded platforms. Software Development & Deployment: Develop efficient Python/ C++ pipelines for real-time 3D vision and geospatial processing. Deploy AI models into production environments, drones, and autonomous systems. Collaboration & Research: Work closely with AI Team and Application product team to develop innovative solutions.