Staff Data Scientist (Core Platform)

Prealize Health•San Jose, CA

8d•$170,000 - $200,000

About The Position

Prealize Health is a predictive analytics company that leverages machine learning and clinical expertise to help patients obtain better care, sooner. Most healthcare today is reactive – care is delivered when someone is already ill. We believe healthcare should be about keeping individuals and their families well to prevent them from ever becoming sick. Building on years of published research from our founders at Stanford University, our mission is to provide patients, providers, and payers with the insights they need to improve health outcomes and prevent adverse medical events. We are committed to helping healthcare organizations "see around the corner" to take a proactive approach to wellness. As a Staff Data Scientist focusing on Foundation Models, you will lead the development of our next-generation patient trajectory and risk prediction systems. You will serve as one of the technical leads for our custom transformer-based architectures, bridging the gap between state-of-the-art research in self-supervised learning and real-world healthcare applications. This is a strategic, high-impact role where you will drive the evolution of our custom healthcare foundation model, shaping how we process millions of claims, lab results, and EHR records to influence the health trajectory of millions of patients.

Requirements

PhD and/or MS in Computer Science, Machine Learning, Statistics, or a related quantitative field.
6–8+ years of experience (with 4+ years specifically building and deploying ML systems in production) with a proven track record of technical leadership.
Mastery of transformer architectures, attention mechanisms, and pre-training/fine-tuning paradigms. Hands-on experience with PyTorch or TensorFlow is mandatory.
Expert proficiency in Python and distributed computing (PySpark/Spark/SQL) for large-scale data processing.
Proficiency in leveraging AI-assisted coding tools (e.g., Claude Code, Cursor, Codex) to accelerate development cycles and enhance code quality.
Strong skills in software design patterns, testing frameworks, CI/CD, and code quality practices.
Demonstrated ability to conduct independent research and translate complex findings into production systems that solve high-ambiguity problems.
Exceptional ability to distill complex technical strategies and research findings for executive stakeholders and cross-functional teams.

Nice To Haves

Experience with large-scale structured healthcare data (Claims, ICD/CPT codes, EHR systems like Epic/Cerner).
Experience with MLOps tooling such as MLflow, Weights & Biases, and cloud platforms (AWS preferred).
Familiarity with causal inference, longitudinal modeling, or self-supervised representation learning.

Responsibilities

Drive the end-to-end building and execution of our custom healthcare foundation models, translating high-level clinical use cases into concrete deep learning architectures and training objectives.
Set the technical roadmap for patient risk prediction and health trajectory modeling, pioneering the use of transformer-based architectures in the healthcare domain.
Establish best practices for deep learning pipelines, including self-supervised pre-training, fine-tuning paradigms, and rigorous evaluation of longitudinal healthcare data.
Own the full ML lifecycle—from data processing and research prototyping to production deployment—while mentoring junior data scientists in modern engineering practices.
Partner with clinicians to encode medical domain knowledge into model architectures and work with Engineering to productionize models with high reliability and low latency.
Experiment with novel architectures and representation learning strategies to ensure our platform remains at the forefront of AI-driven healthcare insights.
Contribute to research initiatives and represent Prealize Health’s technical expertise in the broader machine learning and healthcare data science community.