Data Scientist

Summary

Builds near-real-time healthcare data pipelines from Epic/FHIR/HL7 into Snowflake, develops Snowflake stored procedures and Notebooks for feature engineering, and feeds Snowflake Cortex LLM models while migrating components from Databricks. Requires 5–8+ years in data engineering with deep Snowflake and healthcare domain expertise.

About Role

Mandatory

Healthcare domain exp in recent years

Cortex

What you’ll do

• Build near real time ingestion from Epic/FHIR/HL7 into Snowflake.

• Author Snowflake stored procedures (SQL/Python) and Notebooks to transform/prepare features.

• Feed an existing LLM/Cortex model; ensure stable, well documented feature contracts.

• Migrate/port components from Databricks → Snowflake.

• Implement monitoring/alerts, data quality checks, and concise runbooks.

• Partner with clinicians/data scientists; communicate progress/issues clearly.

What you have

• 5–8+ years in data engineering/data science engineering with Snowflake depth (stored procs, Snowpark/Notebooks, tasks/streams).

• Python for APIs and transformations; healthcare data experience (Epic, FHIR, HL7).

• LLM/GenAI literacy with Snowflake Cortex.

• Near real time ingestion + incremental patterns; strong comms.

• Nice: Databricks experience.

See also

要針對這個職缺調整履歷嗎?

目前無法檢查您與這個職缺的符合程度;請先將履歷加入個人檔案,下次即可查看。

A new version of freehire is available