Overview

Verantos (https://verantos.com) is the global leader in high-validity real-world evidence (RWE) for life sciences. By incorporating robust clinical narrative data, artificial intelligence (AI) technology, and measured validity, Verantos is the first company to generate research-grade evidence at scale across therapeutic areas.

The Verantos Evidence Platform integrates heterogeneous real-world data sources and generates evidence with the accuracy required for market access, health economics and outcomes research (HEOR), medical affairs, and regulatory use. Leveraging data science, AI, and advanced data sources such as electronic health records (EHRs), the platform supports complex clinical studies across multiple therapeutic areas. Today, some of the largest biopharma companies in the world are Verantos customers.

As a Senior Clinical Informaticist, you will help shape how clinical data is transformed and made usable for research by leading efforts in knowledge management, semantic normalization, and data quality. You will collaborate with clinicians, scientists, data scientists, product managers, and engineers to define scalable approaches for mapping clinical concepts, identify where and how key concepts can be captured, develop concept lists for cohort creation, and design clinical data quality checks to ensure datasets meet clinical expectations.

Your work will directly support high-impact research by ensuring that the right concepts are captured, standardized, and accessible across diverse data sources. This is an opportunity to work at the intersection of clinical insight and technical implementation, transforming complex healthcare data into research-grade evidence that advances decision-making at scale.

Responsibilities

Knowledge management

Create and maintain concept groups.
Review customer code lists and recommend updates as needed.
List and define critical variables for each pragmatic registry.

Semantic normalization

Map claims data and health system data to standard concepts in the OMOP Common Data Model (CDM).
Semantically normalize CDM-converted data coming from multiple different health systems and map high priority unmapped concepts

Data usability

Create documentation on how to best use data to generate insights.
Collaborate with customers to help them understand how to leverage data to answer research questions.

Data Quality

Define disease-area–specific data quality testing processes.

Concept Identification

Determine how to best capture concepts needed to answer customer research questions and analyze prevalence of concepts for feasibility assessments.
Specify annotation projects to capture complex clinical ideas.

Qualifications

Required

Clinical degree (MD, DO, PA, NP, or RN) with at least 2 years of clinical experience.
Experience working with standard clinical vocabularies such as SNOMED CT, LOINC, RxNorm, ICD-10-CM, CPT, or HCPCS, including an understanding of their structure and use in representing clinical data.
Familiarity with EHR systems and common clinical documentation practices.
Strong understanding of data captured in structured EHRs, unstructured EHRs (e.g., clinical notes), and claims datasets, including which types of concepts each source best captures.
Excellent verbal and written communication skills for cross-functional collaboration.

Preferred

Advanced training or certification in clinical informatics.
Minimum of 2–3 years of experience in clinical informatics or a closely related role.
Demonstrated expertise in semantic mapping of source clinical terms to standard vocabularies (e.g., SNOMED CT, LOINC, RxNorm, ICD-10-CM, CPT, HCPCS).
Demonstrated analytical and problem-solving skills applied to complex clinical data challenges, such as resolving semantic ambiguity, aligning heterogeneous data sources, or developing scalable mapping solutions.
Experience defining and reviewing data quality tests on clinical datasets.
Experience with the OMOP Common Data Model.
Proficiency with terminology mapping tools.
Familiarity or experience with AI-based extraction from unstructured clinical notes.
Strong understanding of the hierarchical structure and relationships in standard clinical terminologies.
Proficiency in tools for data analysis or transformation (e.g., SQL, Excel, Python, or R).
Prior involvement in projects involving phenotyping or computable cohort definitions.
Proven ability to collaborate with technical teams to design and implement repeatable, scalable approaches to knowledge-driven workflows.
AI-first mindset, with a focus on leveraging automation to develop scalable, repeatable solutions for clinical data normalization, concept identification, and quality assessment.