CVS is embarking on a journey to evolve its existing ExtraCare program into a world-class personalization and loyalty program. This is a top initiative within the company and we have a team dedicated to recruiting the best talent in the world to help propel us to this goal. The company has already invested in state-of-the-art technology and scaling of our loyalty program, now we are focused on optimizing our customer contact strategy. We are looking for the best and brightest to add to our existing Analytics team and help deliver on this initiative.
The Executive Advisor, Lead Data Engineer for Front Store personalization will lead a team of advanced data engineers to design, build, test, productionalize and support components of the Front Store Personalization engine. This role will require an understanding and management of the source data, feature development, machine learning models and pipelines, business rules, the orchestration and productionalization of ML pipelines, structured experimentation in support of iterative testing and learning, and maintenance and enhancements of ML pipelines over time to support an expanding set of Front Store personalization use cases. All of this is critical to driving Front Store growth. This leader will collaborate with Data Scientists, business partners, and IT colleagues to accomplish the execution of the data and analytic roadmap for Front Store Personalization.
CVS is continuing on its journey to deliver our customers' 1:1 personalized experiences through multiple channels. To support this effort, this leader will work across multiple teams to rapidly building, testing, and scaling high-priority use cases that drive increased reach, relevance and rewards for our customers.
Core Job responsibilities:
• Lead coding and architecting of end-to-end applications on modern data processing technology stack (e.g. Hadoop, Cloud, Spark, Azure, Databricks)
• Manage multiple projects and lead collaborative reviews of design, code, data, feature implementation performed by other data engineers in support of maintaining data engineering standards
• Build process to drive continuous integration/continuous delivery, test-driven development, and production deployment frameworks
• Troubleshoot complex data, features, personalized offer build rules issues and perform root cause analysis to proactively resolve product and operational issues (i.e., primary languages Python, Scala and L2-3 production support)
• Productionalize the full pipeline including distributed Machine Learning models (e.g., training/test pipeline, offer eligibility, data layer, feature layer, etc.)
• Connect business context and perspective to define model objective functions, features, business rules, prioritization, measurement, etc.
• Lead conversations with infrastructure teams (on-prem & cloud) on analytics application requirements (e.g., configuration, access, tools, services, compute capacity, etc.)
Identify the skills and experience needed for Data Engineers, Machine Learning Engineers, and adjacent roles, and work with leadership to make required hiring decisions as process evolves over time.
• 8+ years of Big Data, Machine Learning, and Spark experience building and running products and applications at scale, in production, in mission critical situations
• 3+ years leading data engineers and/or analytics-focused teams to deliver complex analytics projects on aggressive timelines
• Full-time, 100% dedicated to Personalization Lab, ideally co-located with Lab in Customer Support Center.
• Platforms: Azure Cloud, Databricks, Hadoop / HDInsight, Spark, Oracle, TD, IntelliJ
• Languages: PySpark, Python, Shell Scripting, SQL, Pig, Java / Scala
• Proficient in Map-Reduce, Spark, Jenkins, Hbase, Pig, No-SQL, Git
• Experience with building data pipelines, data modeling, architecture & governance concepts
• Experience implementing ML models and building highly scalable and high availability systems
• Experience operating in distributed environments including cloud (Azure, GCP, AWS etc.)
• Experience building, launching and maintaining complex analytics pipelines in production
• Experience working via an agile, sprint-based working style
• Experience working side-by-side with business owners, and translating business needs into analytics solutions
• Proven ability to successfully balance near-term results (e.g., ability to design and execute on a 'MVP' model), with long-term goals
• Comfortable balancing quality of output with short timelines required to enable downstream functions
• Bachelor's degree in a field linked to data engineering, business analytics, applied mathematics, computer science, IT, computer applications, engineering or related field is required
• Advanced degreerequired in a field linked to business analytics, statistics, operations research, applied mathematics, computer science, engineering, or related fields