Data Scientist

What This Role Is

Bailey is a clinical AI system that orchestrates LLMs, manages health safety evaluation, and integrates with clinical data to help people navigate their health. Three data scientists build it today, and a new ML/Platform Engineer is standing up the deployment and monitoring infrastructure underneath it.

This role is the analytical half of that infrastructure. As drift detection, safety-weighted quality scoring, and distributional monitoring come online, someone needs to own the statistics behind them: what counts as drift, how confidence calibration is measured, how outputs compare against ground truth in our FHIR data. You'll also go deeper on health scoring analysis (population percentile and distribution work) and support retrieval/embedding evaluation as the team's RAG work matures.

This is real, scoped analytical ownership, not busywork. You'll be mentored by three senior data scientists, but mentorship here means a safety net and a growth path — not supervision. You're expected to scope your own analysis, exercise judgment, and know when and who to ask, not to wait for a spec.

#### What You'll Actually Do

Four real, currently-queued workstreams — not a generic junior-DS template:

• Evaluation science support (pairs with the new ML/Platform Engineer): once the platform engineer builds the pipelines, you own the analytical side — defining drift thresholds, the statistical work behind safety-weighted quality scoring, confidence calibration analysis, and ground-truth comparisons against FHIR data.
• Health scoring depth: a second set of hands on body-system scoring analysis — population percentile/distribution work and outlier handling in the Databricks batching pipeline — currently handled side-of-desk by Sean alone.
• RAG/embeddings evaluation (pairs with Kenan): retrieval quality analysis and embedding evaluation supporting Kenan's move toward embeddings/vector stores, without requiring him to ha