Analytics Engineer

Beacon is a high-growth healthcare AI company seeking an Analytics Engineer to join their data team. The role involves owning the transformation layer of a modern ELT pipeline, ensuring data quality and optimizing pipeline performance to support clinical AI development.

Responsibilities:

• Query complex source systems across EMR, ECG, and DICOM data to identify and map data elements supporting AI training and patient journey analyses
• Develop and maintain data transformation pipelines using dbt and Snowflake, ensuring data quality, lineage, and transparency
• Harmonize multimodal data from multiple health systems into a unified ontological layer, with input from clinical experts
• Perform complex data extraction, manipulation, and summarization to create analytical data models
• Implement data quality tests, CI/CD, and version control best practices across the data modeling pipeline
• Support software engineers in optimizing de-identification and ETL processes across disparate health system cloud environments
• Work with NLP experts to structure and model discrete clinical concepts abstracted from unstructured text
• Collaborate with technical and clinical SMEs and customers to translate research and model requirements into engineering solutions

Requirements:

• Bachelor's degree in a quantitative field (Data Science, Biomedical Informatics, Computer Science, Biostatistics)
• 3+ years in analytics or data engineering roles with hands-on cleaning and structuring of clinical/EHR data
• Strong dbt and SQL proficiency: reusable Jinja macros, custom tests, multi-environment deployments
• 1+ years extracting, curating, and analyzing HIT/healthcare delivery data (EMR, claims, registry); familiarity with FHIR, CDA, CQL, and clinical terminology standards (ICD, CPT, LOINC, SNOMED-CT, NDC, RxNorm) a plus
• Comfort in a cloud environment (Snowflake and/or AWS preferred)
• Proficiency with Git and version control workflows
• Advocate for software engineering best practices (modularity, unit testing, clean documentation) within a data science team
• Comfortable with ambiguity in a fast-paced, early-stage startup environment
• Excellent communication skills, able to translate customer needs into data solutions
• LLM/RAG integration experience (Snowflake Cortex, Bedrock, Azure OpenAI)
• Python for data cleaning/feature engineering
• Exposure to AI/ML modeling teams
• Epic/Cerner/Allscripts familiarity
• Medical ontology or DICOM/imaging experience
• OMOP common data model
• Agile tooling (Jira/Linear)
• dbt Cloud