Data Scientist

Role Overview

You will lead analytical workstreams for SDSC’s surgical analytics platform. The goal is to validate AI-derived surgical metrics against clinical outcomes, create interpretable composite scoring methods, and build scalable data pipelines. You’ll collaborate closely with ML engineers and clinical partners to turn model outputs into clinically meaningful tools.

Responsibilities

Study Design & Validation

• Design and run clinical validation studies correlating AI-derived metrics with outcomes such as complications, resection extent, and procedure duration.

Scoring Methodology

• Develop and refine composite scoring algorithms (e.g., PCA-weighted, Bayesian, or other approaches) to summarize multi-dimensional surgical performance.

Statistical Modeling

• Apply statistical methods including:
  • Logistic regression
  • Mixed effects models
  • Survival analysis
  • Dimensionality reduction

Data Pipeline Development

• Build and maintain Python data pipelines to extract, transform, and analyze data at scale from:
  • MongoDB
  • PostgreSQL
  • S3

Data Quality & Integrity

• Implement data validation checks, investigate discrepancies across sources, and ensure analysis reproducibility.

Clinical Collaboration & Communication

• Partner with surgeons and clinical researchers to define metrics, interpret results, and refine tools based on clinical feedback.
• Produce analysis reports, methodology documentation, and presentations for technical and non-technical stakeholders.

Requirements

• Master’s degree (or equivalent) in statistics, biostatistics, data science, computer science, or a related quantitative field.
• 2+ years of applied data science or quantitative research experience.
• Strong Python skills for analysis and pipeline development: pandas, NumPy, SciPy, scikit-learn.
• Solid statistical methods knowledge: regression, hypothesis testing, dimensionality reduction (PCA/factor analysis), bootstrap inference.
• Experience with SQL databases (PostgreSQL preferred) and NoSQL databases (MongoDB).
• Ability to work independently on ambiguous problems and communicate trade-offs.
• Strong written communication for both technical and non-technical audiences.

Nice-to-Haves

• Experience with healthcare/clinical/biomedical data.
• Familiarity with Bayesian methods or mixed-effects models.
• Cloud experience (AWS—S3, SageMaker, or similar).
• Experience building interactive dashboards / data visualization tools.
• Familiarity with surgical workflow, medical devices, or clinical methodology.