Senior Data Engineer - Real World Data
Formation Bio7 months ago
Responsibilities
- Model and transform raw EHR and claims data into clean, canonical, analytics-ready datasets using SQL, Python, and OMOP.
- Build and manage scalable data pipelines with Dagster, dbt, and Snowflake.
- Conduct real-world data analyses involving disease epidemiology, treatment patterns, patient journeys, and comparative effectiveness.
- Partner with Data Scientists and clinical leads to design and execute reproducible observational studies.
- Implement data validation, completeness, and observability frameworks for trustworthy datasets.
- Apply generative AI techniques to data transformation and analysis workflows.
- Communicate findings to technical and non-technical stakeholders, portfolio teams, and leadership.
Requirements
- 5+ years of data engineering experience, ideally including at least 2 years in healthcare or life sciences with direct EHR or claims exposure.
- Experience with biomedical ontologies and schemas including UMLS, LOINC, ICD9/10, and MeSH.
- Fluency in SQL and Python and experience maintaining production-grade pipelines for analytics or scientific workflows.
- Experience building longitudinal patient cohorts with index date logic, washout periods, and follow-up windows.
- Understanding of causal inference frameworks including potential outcomes and target trial emulation.
- Familiarity with real-world evidence study design, active comparator new user designs, time-to-event outcomes, confounder adjustment, and causal discovery algorithms.
- Hands-on expertise with Snowflake, dbt, and Dagster.
- Bonus: experience in regulated or privacy-sensitive environments and familiarity with PHI or sensitive-data governance.
- Bonus: experience with commercial RWD vendors such as Truveta, Optum, Komodo, or IQVIA and with licensed claims and EHR datasets.
Benefits
- Equity, comprehensive benefits, and generous perks are offered in addition to base salary.
- Hybrid work requiring 3 days per week in the office, primarily in the New York City and Boston metro areas; Research Triangle and San Francisco Bay Area applicants may also be considered.
- Applicants must reside in the listed locations or be willing to relocate.
About Formation Bio
Formation Bio builds AI-driven technology platforms and runs a pharmaceutical development business that designs and executes clinical trials for in-licensed or acquired drugs. It partners with pharma, biotechs, and research groups to take clinical-stage assets through proof of concept and beyond, aiming to reduce trial time and improve data quality. The privately held company is headquartered in New York and originated as TrialSpark before rebranding to Formation Bio.