Job Description: • Experience applying machine learning and computer vision principles to real-world data and working in Scanned and Documented Images to extract relevant text information. • Familiarity with deep learning frameworks such as TensorFlow, Keras, and torch. • Knowledge of tesseract working and fine-tuning. • Document and text extraction. • Image segmentation, object detection, and recognition. • Python Programming is a must, c/c++ is an advantage. • Strong fundamentals in mathematics, especially in linear algebra and computational geometry. • Strong in Image and computer vision-related libraries such as OpenCV, PIL, Dlib, matplotlib, Tensorflow, Pytorch etc. • Developing state of the art models and algorithms. • Hands on experience in CNN and LSTM based models. • Engineering ability to build robustly scalable pipelines. Experience in high performance production (inference pipelines) using tensorRT.• A solid foundation in Python, data structures, algorithms and general software development skills.
Your responsibilities: Build, improve and extend NLP capabilities Research and evaluate different approaches to NLP problems Must be able to write code that is well designed, produce deliverable results Write code that scales and can be deployed to production You must have: Fundamentals of statistical methods is a must Experience in named entity recognition, POS Tagging, Lemmatization, vector representations of textual data and neural networks - RNN, LSTM A solid foundation in Python, data structures, algorithms, and general software development skills. Ability to apply machine learning to problems that deal with language Engineering ability to build robustly scalable pipelines Ability to work in a multi-disciplinary team with a strong product focus