Data Engineer - Clinical Decision Support Solutions

Job Description : Beckman Coulter is seeking a team member to join our Microbiology R&D Development Science functional team. In this role, you will develop and maintain end-to-end data and machine Learning pipelines for clinical and verification studies. We're looking for associates who thrive in a team-oriented, goal-focused environment.

The Data Engineer for Beckman Coulter Diagnostics is responsible for the development and implementation of end-to-end Ops pipelines to support ML model deployment throughout the entire ML lifecycle. This position is part of the data science team located in Sacramento, California, and will be a hybrid role. The data engineer will be a part of the development science functional group and report to the data science manager. If you thrive in a cross-functional team and want to work to build a world-class biotechnology organization—read on.

Responsibilities

• Collaborate with stakeholders to understand data requirements for ML, Data Science, and Analytics projects.
• Assemble large, complex data sets from disparate sources, writing code, scripts, and queries, as appropriate to efficiently extract, QC, clean, harmonize, and visualize Big Data sets.
• Write pipelines for optimal extraction, transformation, and loading of data from a wide variety of data sources using Python, SQL, Spark, and AWS 'big data' technologies.
• Develop and design data schemas to support Data Science team development needs.
• Identify, design, and implement continuous process improvements such as automating manual processes and optimizing data delivery.
• Design, develop, and maintain a dedicated ML inference pipeline on the AWS platform (SageMaker, EC2, etc.).
• Deployment of inference on a dedicated EC2 instance or Amazon SageMaker.
• Establish a data pipeline to store and maintain inference output results to track model performance and KPI benchmarks.
• Document data processes, write data management recommended procedures, and create training materials relating to data management best practices.

Required Qualifications

J-18808-Ljbffr