Job duties
• Work in a cross-functional team of business SMEs, Data Scientists and ML Engineers and Automaton Engineers to deliver best in class solutions that meet and exceed operational SLA for data assets that enable the US real estate economy
• Lead solutioning of complex OCR and NLP problems in the space of data extraction from large volumes of unstructured texts, images, video
• Tune machine learning models for scalability, performance and production readiness
• Deploy machine learning models to production
Technical skills – must have
• Strong hands-on development in Python, focused on data science (ScikitLearn, ScikitImage, OpenCV, PyTesseract)
• Experience with PyTorch/TensorFlow/Keras in building deep learning models, especially in the OCR, Computer Vision and NLP space
• Experience with MLOps – deploying and scaling models in production
• Experience with relational databases such as SQL Server/Oracle/PostGresSQL, and working knowledge of SQL
Technical skills – nice to have
• Experience with GCP / AWS PaaS capabilities for AI/ML development and deployment (AWS SageMaker/GCP DataFlow/AirFlow)
• Experience with APIs (develop and consume) – frameworks such as Django, Express
• Experience with training custom Tesseract models for OCR
• Experience of working in a highly automated software engineering ecosystem enabled with cloud native technologies, CI-CD
Functional skills
• Work in an agile environment, and on complex, ambiguous problems
• Strong verbal and written communication