Data & Semantic Model Architect

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and oversee the Exchange Layer: Develop and manage the Common Data Models (CDMs) that act as the universal language for scientific data across our clientele. Transition the platform from custom, one-off mappings to a standardized "exchange layer" that guarantees interoperability.

• Empower Forward Deployed Engineering: Establish the data contracts and standardized definitions that FDEs depend on. Your models will serve as the toolkit enabling them to deploy more rapidly and with greater confidence, assured that they are building on a stable, consistent semantic foundation.

• Standardization versus Flexibility: Achieve a strategic equilibrium between strict global standards (for cross-customer exchange) and local adaptability. Define the core "immutable" aspects of the model while determining where extensions are permissible.

• Convert high-level business objectives (e.g., "accelerate time-to-insight for biologics") into actionable data modeling strategies. Ensure our semantic roadmap aligns directly with the scientific inquiries that our clients—and our internal teams—need to address.

• Engage actively in designing and implementing intricate ontologies and taxonomies. Model complex scientific relationships (e.g., linking a "Cell Line" in an ELN to "Flow Cytometry Results") with precision.

• Collaborate closely with Engineering to design the software systems that utilize these models. Ensure that the "ideal" ontology does not compromise query performance or system scalability.

• Set the "rules of engagement" for data quality and consistency. Define how data contracts are versioned, enforced, and evolved, ensuring that downstream consumers (AI teams, FDEs, Scientists) can rely on the data structure.

• Partner with Scientific Business Analysts to unravel the complexities of biopharma R&D. Transform vague scientific requirements into precise, machine-readable data structures.

• Architect models that guarantee our data is FAIR (Findable, Accessible, Interoperable, Reusable) and prepared for downstream AI/ML applications.

⛳️ Requirements

• Over 7 years of experience in data architecture, informatics, or technical product leadership, particularly within life sciences, healthcare, manufacturing technology, or the ability to showcase complex, multidomain unification of data models & semantic layers.

• CDM Framework Expertise: Direct, practical experience in implementing and extending Common Data Model frameworks such as HL7 FHIR, OMOP (OHDSI), Allotrope, or CDISC. You should understand the strengths and limitations of each for biopharma R&D.

• Terminology & Standardization: Demonstrated expertise in standardizing disordered, heterogeneous data using both standard vocabularies (including terminology standards & ontologies) as well as proprietary or custom vocabularies. You must have experience in semantically curating (semantic mapping & aggregation; i.e., value set creation) between and across vocabularies as well as discrete instance data.

• Platform & Exchange Experience: Experience in constructing data platforms where standardization and reusability were critical value drivers. You have likely developed models that act as an exchange layer across multiple clients.

• Technical Background: Strong understanding of software development principles; you should be comfortable reading code, comprehending API contracts, and discussing database internals.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance.

• Flexible work hours and remote work options.

• Opportunities for professional development and continuing education.

• A collaborative and innovative work environment.