Data Science Application Designer

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Apache Hadoop, Scala Programming, Machine learning techniques, Data science techniques, PyTorch, TensorFlow, MapReduce, R Programming

Job Description

At Gainwell, we are passionate about helping those most vulnerable get access to high-quality, affordable healthcare. We harness the power of technology to help our clients improve the health and well-being of the members they serve. We believe nothing is impossible when you bring together people who care deeply about making healthcare work better for everyone. Join us and build your career with an inclusive team that thrives on finding innovative solutions to some of healthcare’s biggest challenges.

Job Description

Required Skills:

• Has worked frequently with datasets 10M – 100M rows in size, some of them ugly/messy
• Expert knowledge of SQL queries to process large amounts of data in a set-based fashion
• Thorough understanding of various SQL windowing functions through regular use
• Solid python, including having developed object-oriented designs
• Solid knowledge of Statistical Estimation, Machine Learning, Overfit, False Discovery, etc.
• Solid understanding of indexing, stored procedures, materialized views, etc.
• Solid experience with the use of Dev\Sec\Ops procedures tools for iterative development and CI/CD
• Main-stream BI dashboarding tools such as Power BI, Tableau, SAS, etc.
• Excellent written and verbal communication skills

Preferred Skills:

• Has worked with datasets 100M – 10B rows in size, some of them ugly/messy
• Performed Data Science with Healthcare data
• Knowledge of Functional Programming
• Experience doing Data Science leveraging the elasticity in a major Cloud environment
• Has good knowledge of Repeated Measures Statistical methods including forecasting
• Explainable Machine Learning and Artificial Intelligence / Neural Network Experience 
• Performance Optimization for Data Science development and in production
• Knowledge of Semi-Structured and Un-Structured data, schema-on-read, parsers, NLP packages
• Comfort-level presenting to business stakeholders and executives

Advanced Skills:

• Working knowledge of stacks and CQRS data structures, and state machines that use them
• Use of a Massively Parallel Database Environment
• Understands how to optimize data models for MPP with distribution keys and schemes
• Has used DataBricks for Data Science – knowledge of Scala a plus
• Solid Experience Deriving Insights from Healthcare data
• Experience working toward replicable causal inference in repurposed data
• Medical Training / Experience in Practice