Big Data Engineer - Patient Safety Advisor

Key Skills

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

Job Description

Combining CVS Health and Aetna was a transformative moment for our company and our industry, establishing CVS Health as the nation’s premier health innovation company. Through our health services, insurance plans and community pharmacists, we’re pioneering a bold new approach to total health. As a CVS Health colleague, you’ll be at the center of it all.

We offer a diverse work experience that empowers colleagues for career success. In addition to skill and experience, we also seek to attract and retain colleagues whose beliefs and behaviors are in alignment with our core values of collaboration, innovation, caring, integrity and accountability.

You will partner with business partners to identity opportunities to leverage big data technologies in support of Enterprise Patient Safety with a common set of tools and infrastructure to make analytics faster, more insightful, and more efficient. You will build and architect next-generation Big Data machine learning framework developed on a group of core Hadoop, Spark and cloud technologies. You will design highly scalable and extensible Big Data platforms which enables collection, storage, modeling, and analysis of massive data sets from numerous channels. You will define and maintain data architecture, focusing on applying technology to enable business solutions. You will assess and provide recommendations on business relevance, with appropriate timing and deployment. You will perform architecture design, data modeling, and implement CVS Big Data platforms and analytic applications. You will bring a DevOps mindset to enable big data and batch/real-time analytical solutions that leverage emerging technologies. You will develop prototypes and proof of concepts for the selected solutions, and implement complex big data projects. You will apply a creative mindset to a focus on collecting, parsing, managing, and automating data feedback loops in support of business innovation.

Required Qualifications

• 2-5 years of professional experience including the following:
• Hands-on experience with “big data” platforms including Hadoop and Spark, good understanding of Azune, GCP or AWS environments, as well as experience with traditional RDBMS (eg, Teradata, Oracle).
• Proficiency in “big data” technologies including MapReduce, Spark, Airflow, Kafka, Hbase, Pig, NoSQL databases, etc.
• Proficiency in the following programming languages: Python, shell scripting, SQL (preferably Teradata and PL/SQL syntax) and Hive
• Ability to design and build a framework to orchestrate data pipelines and ML models
• Ability to aggregate huge amount of data and information from large numbers of sources to discover patterns and features necessary to build machine learning models.
• Design and implement end-to-end solutions using Machine Learning, Optimization, and other advanced computer science technologies, and own live deployments.
• Knowledge of Conda, H2O, Airflow / Oozie / Jenkins, Git
• Platforms knowledge: Hadoop, Spark, Kafka, Kinesis, Oracle, Teradata
• Build continuous integration/continuous delivery, test-driven development, and production deployment frameworks
• Lead conversations with infrastructure teams (on-prem & cloud) on analytics application requirements (e.g., configuration, access, tools, services, compute capacity, etc.)

  Preferred Qualifications

• Exposure to Healthcare Domain knowledge
• Proficiency in Python
• Experience with cloud computing environment (ideally Microsoft Azure) and the organizational risks of transitioning from on-prem to cloud infrastrucuture.
• Experience with automation tools: eg, Jenkins, Airflow, Control-M
• Experience operating in distributed environments including cloud (Azure, GCP, AWS etc.)
• Familiarity with data modeling, data architecture and governance concepts
• Familiarity with specialized areas such as Optimization, NLP, Reinforcement Learning, Probabilistic Inference, Machine Learning, Information Retrieval, Recommendation Systems.
• Familiarity with frameworks for either Machine Learning or NLP (Scikit-Learn, SpaCy, Pytorch, Spark NLP)

  Education

  Bachelor’s Degree in Computer Science, Engineering, Astronomy/Physics, Economics, Math or related fields is required

  Advanced Degree in Computer Science, Engineering, Astronomy/Physics, Economics, Math or related fields preferred