Job Description:
• As a Python / Computer Vision Developer, you will be responsible for the design, development, and implementation of innovative computer vision and AI-based solutions in the logistics and automation domain.
• The primary role will include developing and optimizing algorithms for object detection, recognition, tracking, and OCR/ANPR using Python and modern deep learning
frameworks.
• Responsibilities include designing, coding, testing, debugging, and documenting programs as well as supporting activities aligned with corporate AI/ML and systems architecture.
• You will ensure support in analysis, model design, and system integration during all phases of solution delivery, including recommending the most effective approaches for deployment and scalability.
• Your tasks will also include working on new research concepts, training pipelines, and AI model deployment across real-time video streams and edge/cloud environments.
• Typically requires 5–7 years of applicable experience in Python, machine learning, and computer vision, with hands-on exposure to frameworks such as OpenCV, PyTorch,
TensorFlow, or PaddleOCR/YOLO.
Skill Requirements:
• Strong proficiency in Python (3.x) with focus on AI/ML and computer vision development.
• Solid experience with OpenCV and at least one major deep learning framework:
PyTorch, TensorFlow, Keras, or PaddlePaddle.
• Hands-on experience with object detection models (YOLO, Faster R-CNN, SSD, etc.) and OCR frameworks (e.g., PaddleOCR, Tesseract).
• Experience with real-time video/image processing (RTSP streams, edge devices, GPU acceleration).
• Good knowledge of data preprocessing, augmentation, and annotation tools (LabelImg, PPOCRLabel, CVAT).
• Familiarity with containerization (Docker), APIs, and cloud platforms (Azure, AWS, GCP) for model deployment.
• Understanding of SQL/NoSQL databases for storing and retrieving processed data.
• Knowledge of Git, CI/CD pipelines, and Agile methodologies.
