Backend / Data Engineer

Clinical reasoning is only as good as the data feeding it. You will own the data layer end-to-end: ingestion from EHR systems, normalization across terminologies, time alignment across signals, and the pipelines that hand clean longitudinal patient records to the trajectory engine.

Today the engine runs against research databases. The next phase is real hospital data: Epic, Cerner, Meditech, with their format quirks, missing fields, and inconsistent coding. You will design the layer that absorbs that reality without bleeding it into the engine.

• Designing and building EHR ingestion pipelines for hospital pilot sites
• Normalizing clinical data across terminologies (ICD-10, SNOMED CT, LOINC, RxNorm) and across vendor formats (FHIR, HL7, OMOP)
• Handling time alignment, deduplication, and longitudinal merging across multiple data sources per patient
• Building data quality checks, monitoring, and clinical reasonableness validation
• Partnering with hospital IT teams on technical integration
• Designing the data contracts the trajectory engine depends on

In your first 12 months: production-grade EHR ingestion running for the first hospital pilot site, normalized OMOP-style data layer in place, automated data quality monitoring, and clear documentation other engineers can build against.

• Strong Python and SQL
• Four-plus years building data pipelines at scale
• Experience with healthcare data formats (FHIR, HL7, OMOP, or similar) or equivalent regulated-data work
• Comfort with data quality challenges: missingness, deduplication, multi-source reconciliation
• Working knowledge of relational databases; PostgreSQL preferred
• Ability to work directly with clinical and engineering stakeholders

Deseable

• EHR integration experience (Epic, Cerner, Meditech)
• Working knowledge of clinical terminologies
• Streaming or event-driven data pipelines (Kafka, Pub/Sub)
• DBT, Dagster, or similar transformation/orchestration frameworks
• Prior experience with HIPAA-regulated production environments

Healthcare data experience is preferred but not required. Strong general data engineering skill plus willingness to learn the clinical data world is enough.

Chroneme is building neuro-symbolic AI for medicine: one record of each person, in order and in context, read by learned models and decided by explicit clinical rules that state their reason and their source. It tells the care team who needs attention and why, and prepares the work for a clinician to sign.

We are a small team in Birmingham, Michigan, building with clinicians and validating under a pre-registered protocol. You will work directly with the founders, with no layers between you and the work. Early team members get meaningful equity.

1. 1An introductory call to discuss your background and interest (30 minutes, with a cofounder)
2. 2A technical conversation walking through a pipeline you built, followed by a discussion of the data integration challenges in front of us. (60 minutes, with the founding team)