Data Scientist (CV-Parser Lite, Automated Resume & VISA Data Labeling)
TextEntity Ner Classification
Led data cleaning, extraction, and standardization tasks on candidate and VISA information for CV-Parser Lite using Python and NLP. Developed scalable automated pipelines to label entities such as names, skills, and work authorization categories from resume data. Integrated LLM-powered solutions to automate text classification and entity recognition to increase efficiency and accuracy. • Labeled key metadata fields (e.g., name, skills, location) in CV text. • Mapped country-specific VISA/work authorization to standardized labels. • Resolved annotation errors with multi-threaded error handling. • Automated entity extraction and query generation with LLMs.
Led data cleaning, extraction, and standardization tasks on candidate and VISA information for CV-Parser Lite using Python and NLP. Developed scalable automated pipelines to label entities such as names, skills, and work authorization categories from resume data. Integrated LLM-powered solutions to automate text classification and entity recognition to increase efficiency and accuracy. • Labeled key metadata fields (e.g., name, skills, location) in CV text. • Mapped country-specific VISA/work authorization to standardized labels. • Resolved annotation errors with multi-threaded error handling. • Automated entity extraction and query generation with LLMs.
2024 - Present