Data Science Lead Analyst

• Using your knowledge of ML / AI, you will build technologies to generate descriptive and predictive insights on how we can better serve throughout their customer journey, with digital assets we have.
• Your work will require deep acquaintance with Evernorth s data, seeking to find ways to deliver value through advanced feature engineering.
• From your models, you will deliver actionable insights that can be incorporated into existing digital and marketing solutions as we'll as informing on new strategy .
• In addition to collaborating with Data Science Management and Business Analytics partners to establish strategic priorities, you will work closely with Data & Engineering to deliver code that is robust and ready to scale.

• Data acquisition, QC and exploratory analysis on transactional member data
• Create models using ML / AI techniques to predict risk and identify actionable insights
• Deliver clean, reusable, and scalable code
• Work closely with Data & Engineering to deploy models
• Partner with senior team members on the latest analytic techniques, technologies, and methods

Required Education

• MS/PhD in Computer Science, Math, Statistics, or in any technical field that provides a solid basis for analytics or equivalent work experience

R equired Skills

• The ideal candidate for this role will have strong coding skills in Python, a passion for creating technology to improve the healthcare systems, and an attitude of creativity and continual learning.

R equired Experience

• 5-8 years of industry experience with Data Mining, Statistical Analysis and leading ML / AI methods; XGBoost , Light GBM, deep learning, reinforcement learning, optimization required
• 5-8 years of experience with Python, PySpark and its data science libraries
• Excellent oral and written communication skills

Desired Experience

• Prior experience working in the healthcare industry, services ops or digital domain
• Experience with deploying predictive models into production
• Experience working with business stakeholders