Data Scientist - Evernorth (Hybrid)

Key Skills

Python Programming, SQL, Apache Hadoop, Machine learning techniques, Keras software library, Natural Language Processing (NLP), TensorFlow, Apache Hive, PySpark, SPARK Programming, Neural Networks, Statistical modeling

Job Description

Evernorth, Cigna's health services division, is in search of a Data Scientist to join our Digital Product team based out of the Santa Monica, California office. This team is responsible for developing a personalization platform to help members find the best providers for their healthcare needs. The role will be responsible for setting up data science best practices, developing machine learning models and reporting test results to key stakeholders. The ideal candidate is also a motivated, self-starter that brings a fresh perspective and passion to solve complex business and technical challenges in a fast-paced and team-oriented environment. The role will report to the Director of Product Management.

Key Responsibilities:

• Work with large, complex healthcare provider, member and claim datasets, applying advanced analytical methods as needed.
• Conduct end-to-end analysis that includes data gathering and requirements specification, processing, analysis, ongoing deliverables, and presentations.
• Design and architect the personalization platform
• Translate healthcare business problems into data science questions, develop solutions and drive result
• Explain data science findings and machine learning models to stakeholders.
• Implement and execute production-level machine learning models
• Collaborate with engineering teams to build data-based products and help integrate into the products and operational processes.

Required Qualifications:

• 2+ years of experience as a Data Scientist or equivalent proven experience in advanced modeling
•  MS degree or higher in Statistics, Data Science, Applied Math, Econometrics, Computer Science, or other related fields
• Solid professional experience using Python, PySpark, and SQL for purposes of model development
• Proven track record of launching production level data products using big data technologies (such as Hadoop, Spark, Hive, etc.)
• Deep understanding of statistical modeling, machine learning, Natural Language Processing (NLP), and Neural Networks (TensorFlow/Keras) and a track record of solving problems with these methods

Desired Qualifications:

• Experience with working with health provider datasets
• Knowledge of data engineering, application architecture, ETL processes and SQL.
• Experience developing recommendation engine is a plus

This position is hybrid, meaning most of the work will be completed from home. Employees will be expected to be on-site in Santa Monica at least 3 days per month.