Senior Data Engineer II - Electronic Health Records (EHR)

Formation Bio • Boston, MA

35d • $230,000 - $280,000 • Hybrid

About The Position

We’re looking for a Senior Data Engineer to join the Data Platform team at Formation Bio to help transform Electronic Health Records (EHR) data into structured, analytics-ready assets. In this role, you’ll be partnering closely with our Data Science team to model, transform, and refine data for operational and scientific use cases. This position sits at the intersection of healthcare data engineering, modern data platform infrastructure, and generative AI. While your initial focus will be on building high-quality EHR models for Formation Bio platform, you’ll also contribute to our broader data architecture by leveraging tools like Snowflake, Dagster, and dbt to enable scalable, governed, and high-reliability pipelines. The ideal candidate combines deep data engineering experience with both GenAI fluency (e.g., LLM-based entity extraction, summarization, classification) and strong technical expertise with modern data tooling. You’ll play a key role in shaping how healthcare data becomes discoverable, structured, and impactful across the organization.

Requirements

• You have 5+ years of experience in data engineering, ideally with at least 2 years working in healthcare or life sciences, including direct exposure to EHR datasets.
• Experience with ontologies and biomedical schemas (e.g. UMLS, LOINC, ICD9/10, MeSH, etc.)]
• Experience and understanding of modalities found within EHR datasets incl. Billing claims, lab results, visit notes, images
• Experience in biomedical feature engineering, e.g. variable transformations and derivatives
• You’re fluent in SQL and Python, and you’ve built and maintained production-grade pipelines that support analytics, science, or operational workflows.
• You have hands-on expertise with modern data infrastructure, including:
• You’re experienced in applying GenAI techniques within pipelines, including prompt engineering, LLM-based entity extraction, and classification/summarization workflows.
• You value clarity, documentation, and structured thinking—especially when working with complex data like healthcare records.
• You have a growth mindset and are excited to build bridges between isolated data environments and governed, shared models that power scientific innovation.

Nice To Haves

• You’ve worked in regulated or privacy-sensitive data environments, and you’re familiar with governance models for PHI or sensitive data

Responsibilities

• Model and transform raw EHR data into clean, canonical, and analytics-ready datasets using SQL, Python, and clinical standards like FHIR, HL7, or OMOP.
• Build and manage scalable data pipelines using Dagster for orchestration, dbt for transformation, and Snowflake as the primary compute and storage engine.
• Collaborate with Data Science and product stakeholders to co-develop cohort logic, derived features, and structured outputs that meet real-world scientific needs.
• Apply Generative AI techniques within transformation layers—using LLMs for named entity recognition, document summarization, classification, and schema alignment.
• Write robust, testable, and version-controlled code that adheres to CI/CD and data governance best practices.
• Implement data validation and observability frameworks to ensure quality, trust, and reproducibility of datasets.
• Document transformation logic, assumptions, and data lineage in collaboration with metadata and cataloging systems.
• Contribute to the evolution of the Data Platform by helping define standards, patterns, and best practices around GenAI and platform-scale data engineering.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 101-250 employees