Carenostics is seeking an experienced (5-12 years) data engineer with a passion for transforming healthcare to join our team (currently 10+ employees) as Senior ML Data Engineer. Responsibilities include:
● Drive the end-to-end ML engineering work for the CKD AI project, including, managing database, feature extraction, data quality, data ingestion; CI/CD, MLOps, incorporating novel data sources (claims, SDoH), ML experimentation and deployment
● Design, develop, and deploy the data pipelines to enable extraction of features from raw EHR data, and productionalize infrastructure to enable interoperability across institutions
● Support the integration of ML-based clinical decision support models directly into clinician workflow to help clinicians identify high-risk chronic disease patients - enabling earlier intervention and preventative treatment for undertreated/underserved patients
● Define and enforce data quality standards
Come transform healthcare with us!
Carenostics is a healthcare AI startup dedicated to addressing the underdiagnosis, undertreatment, and health inequities of chronic disease through AI and ML on patient electronic health record (EHR) data. To date, Carenostics has:
● Deployed its first ML product for the early detection of chronic kidney disease (CKD) at Hackensack Meridian Health (HMH), serving 6 Million patients.
● Received funding from the NSF, Bayer Pharmaceuticals, and the VA.
● Gained access to run AI/ML over 15M longitudinal patient EHRs from leading health systems and claims for 50M patients from leading payors & CareJourney.
Our CEO and world-class team have taken 20+ healthcare AI solutions to market, generating $5B in revenue and impacting the lives of millions of patients worldwide.
Candidate qualifications:
● 5+ years of experience building end-to-end data science workflows: from data engineering / building scalable data pipelines, to analysis/modeling, to ML deployment
● 5-12 years of work experience with SQL, data warehouses, data lakes, relational DBs (ideally including PostgreSQL) developing large scale data & analytics solutions
● 5+ years of developing data intensive software using Python in a production setting (ideally including building and deploying production ML systems with Agile methodology)
● Strong coding skills in Python and Java
● Experience working on real-world problems and passion for having social impact
Additional desirable qualifications include:
● Experience with managing & developing on cloud platforms such as AWS, Azure or GCP
● Familiarity with standard machine learning packages (SciKitLearn, PyTorch, TensorFlow)
● Experience working with data engineering and software development teams
● Experience with healthcare data (e.g., EHR, claims, HL7, FHIR)
Benefits of this role:
● Competitive salary, benefits and options at startup poised for hyper-growth
● Key player in mission-driven company tackling one of society’s greatest challenges
● Access to rich healthcare data from leading institutions (e.g., VA, HMH, payers) for deploying models with immediate real-world impact on tens of millions of patients
● Significant access to and mentorship from proven leaders in healthcare machine learning (from institutions including CMU, MIT, HMH, VA, Cerner, and Siemens)
● Opportunities to publish cutting-edge research on novel applications of AI to healthcare in leading journals and conferences (recent paper accepted to NeurIPS this year)
● No relocation required
You will report directly to the co-founders, receive direct mentorship from executives, principal engineers, architects and practitioners with decades of experience applying AI and ML to healthcare problems, and directly shape the direction of the company as we transform healthcare. As an early hire, you will have opportunities for rapid upward mobility: if desired, you can transition to a Director role and be empowered to scale the data engineering and software development teams. Additional opportunities include working directly with clinicians on the interface / workflow and engaging with the startup team on conversations beyond data science (e.g., commercialization, growth strategy, leading new client deployments).
Learn more about us, our partnerships, and journey this past year at: www.carenostics.com
If you want to be part of our mission to transform healthcare into a data-driven paradigm where decisions to improve lives are driven by insights learned from millions of EHRs and claims, please reach out to careers[at]carenostics.com with your resume.