Data Scientist

Job Summary

To support a growing clinical AI system, the full-time Data Scientist will own the analytical aspects of drift detection, safety-weighted quality scoring, and health scoring analysis while collaborating closely with a new ML/Platform Engineer in a remote environment.

Key responsibilities

• Define drift thresholds and conduct statistical analysis for safety-weighted quality scoring and ground-truth comparisons against FHIR data
• Assist in body-system scoring analysis and outlier handling within the Databricks batching pipeline
• Evaluate retrieval quality and embedding performance to support the development of embeddings/vector stores

Required qualifications

• Strong foundation in statistics and machine learning, with the ability to reason about distributions and evaluation design
• Proficiency in Python, demonstrated through personal projects or contributions on platforms like GitHub
• Understanding of systems and control flow to effectively direct coding agents
• Ability to work independently in ambiguous situations, scoping analyses and asking targeted questions when needed
• Demonstrated ambition and ownership of outcomes, with a proactive approach to knowledge gaps