Lead Data Scientist

Job Summary

At HCA Healthcare, we are committed to providing our patients and care providers with the highest quality of healthcare services. HCA’s Care Transformation and Innovation (CT&I) team delivers a step change in that direction through clinically led integration of digital and AI technologies into care.

Data Scientists within CT&I will play a critical role in helping us achieve this goal by actively solving for and implementing a broad range of data science solutions to drive transformational change. This includes delivery of data science products from incubation to deployment to monitoring; including solutioning for the business need, data analysis, feature engineering, building and validating models, deploying solutions to enterprise production platforms, and monitoring model performance and reliability.

This individual will be responsible for actively delivering production grade data science products; including implementing best practices, frameworks, tooling, and documentation.

They will be expected to bring hands-on expertise in predictive analytics, classification, image recognition, NLP, anomaly detection, machine learning, EDA, feature engineering, optimization, statistics, and generalized business problem solving by creatively applying AI/ML.

What you will do:

• DATA INJECTION: Design and implement incoming data for feature engineering and machine learning

• FEATURE CREATION AND TRANSFORMATION: Create features with usable predictive power by using domain knowledge of healthcare data, statistics, and data science

• FEATURE EXTRACTION AND SELECTION: Extract features via cluster analysis, text analytics, principal components analysis and related methodologies to identify useful information without distorting original relationships or significant information in order to performance tune and promote scalability of the model

• EXPLORATORY DATA ANALYSIS: Conduct data exploration and analysis to identify relevant patterns, trends, and relationships; understand the data deeply to appropriately align the data features with the appropriate machine learning methodologies

• MODEL EXPERIMENTATION: Apply various statistical and machine learning techniques to develop, tune, and optimize predictive modeling to align with the use case requirements

• DELIVERY: Deploy code using best practices

• DOCUMENTATION: Document and present data science strategies and insights and solutions

• MONITORING: Build and maintain pipelines, code, and processes to monitor the proper functioning of enterprise grade data science products

• DATA AND OUTPUT QUALITY: Ensure high quality and integrity throughout the entire data science process

• PRODUCT DEVELOPMENT MINDSET: Collaborate with stakeholders, data scientists, data engineers, and product managers to build and deliver high-quality data products

What qualifications you will need:

• 6+ years of overall experience in various aspects of data science and machine learning (for Lead level)

• Expert experience in SQL and Python

• Experience with structured and unstructured data (ie. tabular, text, images, video, etc)

• Experience with SQL relational and non-relational databases

• Experience with data processing and ETL tools (e.g Apache Spark)

• Experience with data visualization and data monitoring tools

• Experience with modern software engineering practices (e.g. automated testing, continuous integration and continuous development)

• Experience with Docker

• Experience with cloud deployments in GCP or another cloud platform

• Experience with Agile development methods and tools (e.g. Azure Dev Ops)

• Excellent communication and collaboration skills, with the ability to work effectively across multiple teams and stakeholders

• Ability to tell a story using data and insights that drives action and change

• Domain knowledge of healthcare data preferred

• Expertise in healthcare protocols and formats such as HL7, FHIR, DICOM preferred

• Expert in the regulatory aspects of the healthcare domain preferred

• Experience in GCP platform preferred