Data Scientist I - Windreich Department for AI & Human Health Research

Mount Sinai Health System • New York, NY

1d

About The Position

The Data Scientist will join the NHLBI-funded PREVENT pAKI project, which uses federated and pooled machine learning on electronic health record data from 15 hospitals and more than 320,000 non-cardiac surgery patients. The project aims to predict postoperative acute kidney injury (pAKI) and identify personalized prevention strategies that generalize across patient subgroups. The role works directly with the principal investigator, a nephrologist co-investigator, and site teams at Mount Sinai, UCLA, and Vanderbilt. It applies and develops machine-learning methods, with an emphasis on statistical rigor, reproducibility, and scientific publication.

The ideal candidate is a Master’s graduate with at least two years of healthcare data science or analytics experience. The candidate will build pAKI patient cohorts and develop deep-learning models to predict pAKI risk in future patients, independently conduct statistical analyses, and communicate and collaborate effectively with stakeholders and peers. Within one year, the candidate is expected to have deployed a successful deep-learning model using PyTorch and be able to present its outcome-prediction performance to technical and non-technical audiences.

Requirements

• Master’s degree in a quantitative discipline, such as Statistics, Operations Research, Bioinformatics, Economics, Computational Biology, Computer Science, Information Technology, Mathematics, or Physics, or equivalent practical experience.
• At least 2 years of work experience in data science, software engineering, or data analysis.
• Experience with at least one programming language among Scala, Python, Java, C, or C++.
• Experience with database languages such as SQL or NoSQL.
• Familiarity with cloud computing platforms such as AWS, Azure, or GCP.
• Experience with version control systems such as Git.
• Knowledge of big data technologies such as Hadoop or Spark.
• Self-motivated, with demonstrated ability to work independently and exercise independent judgment in developing complex techniques or programs in a dynamic environment.

Nice To Haves

• Experience with EHR data (OMOP preferred) and clinical prediction modeling, including calibration and external validation.
• Causal inference or heterogeneous treatment effect methods, such as grf or policytree.
• Deep learning (PyTorch or graph neural networks), federated learning, or algorithmic fairness evaluation.
• Cloud or HPC experience with AWS, Azure, or GCP.
• PhD.
• First-author publications.

Responsibilities

• Build and curate analytic cohorts from OMOP-mapped and perioperative data warehouse sources, including AKIN/KDIGO acute kidney injury outcome definitions and quality checks for consistency, plausibility, and missingness.
• Develop and validate prediction models, including gradient-boosted trees and graph neural networks, with uncertainty quantification; report discrimination, precision-recall, and calibration.
• Implement and compare site-specific, pooled, and federated (stacked) models across three institutions and subgroups, and implement mitigation strategies for underperforming groups.
• Apply causal inference methods, including causal forests and policytree, and reinforcement learning to identify sub-phenotypes and personalized prevention strategies.
• Maintain version-controlled, reproducible code and documentation sufficient for external replication, and prepare code and models for public release.
• Contribute to manuscripts, abstracts, and presentations, and communicate methods and results clearly to clinicians and non-technical audiences.
• Coordinate with site teams on data requests, local model training, and project milestones.
• Stay current with federated learning, causal machine learning, and algorithmic fairness literature, and propose methodological improvements.
• Perform other duties as assigned.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level