Data Scientist (Remote)
Role details
Job location
Tech stack
Job description
Duties: The Data Scientist Availity LLC in Jacksonville, FL will design, develop and implement predictive, statistical, and machine learning models to support operational and product decisions. Extract, clean, and transform structured and unstructured data from multiple sources using Python and SQL. Perform exploratory data analysis (EDA) to identify trends, anomalies, and actionable insights within large datasets. Develop and maintain automated data, machine learning pipeline and ETL processes to enable scalable model training and evaluation. Research and prototype new algorithms and statistical methods to enhance product integrity and user experience. Develop automated processes using NLP techniques to uncover hidden insights from text data. Collaborate with engineering, product and clinical team to define data requirements and integrity. Document modeling approaches, data mining techniques, and results for internal review. Position is 100% remote., NOTICE: Federal law requires all employers to verify the identity and employment eligibility of all persons hired to work in the United States. When required by state law or federal regulation, Availity uses I-9, Employment Eligibility Verification in conjunction with E-Verify to determine employment eligibility. Learn more about E-Verify at http://www.dhs.gov/e-verify.
Requirements
Requirements: Master's degree in Data Science, Analytics, Information Systems, or a directly related field, plus 1 year of experience as a data scientist or related occupation. Must have 1 year of experience with each of the following: (1) Restful APIs; (2) designing, developing, and maintaining end-to-end machine learning pipelines on Azure Databricks using Pyspark, scikit-learn and pandas for balanced and imbalanced datasets; (3) developing models with NLP techniques using Huggingface, NLTK, Sentence BERT model, transformers, and fine-tuning; (4) designing medical document classification model using XGBoost and neural networks; (5) experimenting, designing and tracking machine learning models with MLFlow and Hyperopt library; (6) building solutions for healthcare specific data problems, following PHI/PII and ensuring HIPPA compliance; and (7) continuous integration, testing, deployment, and release methodologies.