Sr. AI Computer Vision Engineer

As a Senior AI Computer Vision Engineer at Ezio Solution, you will be a valuable member of the AI team, contributing to the development, optimization, and deployment of cutting-edge computer vision algorithms and AI models for various real-world applications. **Key Responsibilities:** - Design, develop, and deploy computer vision models for tasks including object detection, tracking, classification, and recognition. - Collaborate with image/video datasets to annotate, preprocess, and augment data to enhance training processes. - Research and implement advanced models like YOLO, Faster R-CNN, Mask R-CNN, Deep SORT, etc. - Create pipelines for real-time video processing and efficient AI inference with optimized latency. - Optimize models for edge deployments on devices like Jetson Nano/Xavier, Raspberry Pi, etc., using ONNX, TensorRT, or OpenVINO. - Engage with cross-functional teams such as Data Science, Backend, and DevOps to ensure comprehensive AI deployment. - Stay updated with the latest advancements and research in the realms of computer vision and deep learning. **Key Skills & Qualifications:** - Proficient in Python and relevant libraries like OpenCV, NumPy, and scikit-learn. - Hands-on experience with deep learning frameworks such as TensorFlow, PyTorch, and Keras. - Solid understanding of CNN architectures and practical expertise in training and assessing models. - Familiarity with image annotation tools and dataset creation tools like LabelImg, CVAT, etc. - Previous exposure to deploying models on edge devices or in cloud environments would be advantageous. - Additional knowledge in multimodal AI, pose estimation, 3D vision, or SLAM is a plus. **Nice to Have:** - Familiarity with MLOps tools like MLflow, Weights & Biases. - A degree in Computer Science, AI/ML, Data Science, or related field would be beneficial. - Experience with containerized deployments using Docker. - Knowledge of REST API development for model serving, such as FastAPI or Flask. As a Senior AI Computer Vision Engineer at Ezio Solution, you will be a valuable member of the AI team, contributing to the development, optimization, and deployment of cutting-edge computer vision algorithms and AI models for various real-world applications. **Key Responsibilities:** - Design, develop, and deploy computer vision models for tasks including object detection, tracking, classification, and recognition. - Collaborate with image/video datasets to annotate, preprocess, and augment data to enhance training processes. - Research and implement advanced models like YOLO, Faster R-CNN, Mask R-CNN, Deep SORT, etc. - Create pipelines for real-time video processing and efficient AI inference with optimized latency. - Optimize models for edge deployments on devices like Jetson Nano/Xavier, Raspberry Pi, etc., using ONNX, TensorRT, or OpenVINO. - Engage with cross-functional teams such as Data Science, Backend, and DevOps to ensure comprehensive AI deployment. - Stay updated with the latest advancements and research in the realms of computer vision and deep learning. **Key Skills & Qualifications:** - Proficient in Python and relevant libraries like OpenCV, NumPy, and scikit-learn. - Hands-on experience with deep learning frameworks such as TensorFlow, PyTorch, and Keras. - Solid understanding of CNN architectures and practical expertise in training and assessing models. - Familiarity with image annotation tools and dataset creation tools like LabelImg, CVAT, etc. - Previous exposure to deploying models on edge devices or in cloud environments would be advantageous. - Additional knowledge in multimodal AI, pose estimation, 3D vision, or SLAM is a plus. **Nice to Have:** - Familiarity with MLOps tools like MLflow, Weights & Biases. - A degree in Computer Science, AI/ML, Data Science, or related field would be beneficial. - Experience with containerized deployments using Docker. - Knowledge of REST API development for model serving, such as FastAPI or Flask.