Job profile:
• Develop and enhance OCR (optical character recognition) systems
• Explore and integrate alternative libraries
• DocTR by Mindee for end-to-end document analysis.
• Implement OpenCV or other Computer Vision libraries for enhancing images to read from documents.
• Implement and fine-tune document understanding models such as Layout LM and YOLOv 8 integrating visual, textual, and layout information from documents for improved classification and extraction.
• Utilize NLP techniques and tools, including NLTK and Hugging Face.
• Design and apply Neural Networks using frameworks like TensorFlow, Keras, and PyTorch for tasks in image segmentation, object detection, and image classification.
• Develop and maintain ETL project using python libraries of pandas, numpy.
• Develop tactical automations using python Robo framework.
• Develop and maintain python codes for use in RPAs frameworks.
• Engage in Deep Learning projects, leveraging advanced architectures to solve complex problems in computer vision and natural language processing.
• Collaborate with cross-functional teams to integrate AI models into broader systems, ensuring robustness and scalability.
• Manage the entire data lifecycle from collection and pre-processing to modelling
• Post-analysis in a production environment.
Technical skills: Python, NLTK, Sklearn, tensoor Flow, pyTorch, NLP technology, Git,OCR, layoutLM, YOLOv 8, Keras, artificial intelligence
Soft skills: Good communication skills, leadership skills, interpersonal skills, analytical skills, , interpersonal skills
Educational Qualification: Master degree in Computer Science, Artificial intelligence or related field
Experience: 5 - 7 years of relevant experience