Applied Computer Vision Engineer (Deep Learning)

Role Overview: You will be part of a team developing advanced AI-driven image analysis systems to extract structured geometric features from visual data. Your main responsibility will involve designing and deploying deep learning models for object detection, segmentation, and feature extraction from high-resolution images. Key Responsibilities: - Design and develop deep learning models for tasks such as object detection, semantic and instance segmentation, and feature extraction. - Build and train models using modern deep learning frameworks like PyTorch. - Develop detection pipelines using architectures such as YOLO for real-time detection. - Implement segmentation pipelines using models like SAM, Mask R-CNN, or Detectron2. - Design and implement image preprocessing and augmentation strategies to enhance model robustness. - Develop post-processing algorithms for precise coordinate extraction and vectorized feature representations. - Create and maintain training pipelines, evaluation metrics, and dataset management workflows. - Collaborate with engineering teams to integrate models into production environments. Qualification Required: - Strong programming skills in Python. - Hands-on experience with PyTorch or similar deep learning frameworks. - Experience in training object detection models like YOLO and Faster R-CNN. - Familiarity with image segmentation models such as Mask R-CNN and SAM. - Understanding of computer vision fundamentals. - Proficiency in OpenCV and image processing techniques. - Experience with data augmentation libraries like Albumentations or torchvision. - Familiarity with annotation tools such as CVAT, Label Studio, or Roboflow. - Experience working with GPU environments for model training. - Knowledge of Docker and containerized ML environments. Additional Company Details (if present): The company offers an opportunity to work on cutting-edge applied computer vision problems, access to large real-world image datasets, high-performance GPU training environments, and the ability to build models from research to production systems. (Note: Screening questions are not included in the job description.) Role Overview: You will be part of a team developing advanced AI-driven image analysis systems to extract structured geometric features from visual data. Your main responsibility will involve designing and deploying deep learning models for object detection, segmentation, and feature extraction from high-resolution images. Key Responsibilities: - Design and develop deep learning models for tasks such as object detection, semantic and instance segmentation, and feature extraction. - Build and train models using modern deep learning frameworks like PyTorch. - Develop detection pipelines using architectures such as YOLO for real-time detection. - Implement segmentation pipelines using models like SAM, Mask R-CNN, or Detectron2. - Design and implement image preprocessing and augmentation strategies to enhance model robustness. - Develop post-processing algorithms for precise coordinate extraction and vectorized feature representations. - Create and maintain training pipelines, evaluation metrics, and dataset management workflows. - Collaborate with engineering teams to integrate models into production environments. Qualification Required: - Strong programming skills in Python. - Hands-on experience with PyTorch or similar deep learning frameworks. - Experience in training object detection models like YOLO and Faster R-CNN. - Familiarity with image segmentation models such as Mask R-CNN and SAM. - Understanding of computer vision fundamentals. - Proficiency in OpenCV and image processing techniques. - Experience with data augmentation libraries like Albumentations or torchvision. - Familiarity with annotation tools such as CVAT, Label Studio, or Roboflow. - Experience working with GPU environments for model training. - Knowledge of Docker and containerized ML environments. Additional Company Details (if present): The company offers an opportunity to work on cutting-edge applied computer vision problems, access to large real-world image datasets, high-performance GPU training environments, and the ability to build models from research to production systems. (Note: Screening questions are not included in the job description.)