Real World Data Lead

At Twin Health, we empower people to improve and prevent chronic metabolic diseases, like type 2 diabetes and obesity, with a new standard of care. Twin Health is the only company applying AI Digital Twin technology exclusively toward metabolic health. 

We start by building a dynamic model of each person’s metabolism — drawing on thousands of data points from CGMs, smartwatches, and meal logs — that maps their personal path to better health. Guided by a dedicated clinical care team, our members have lowered their A1C below the diabetes range, achieved lasting weight loss, and reduced or even eliminated medications, all while living healthier, happier lives.

Our team at Twin Health is passionate, talented, and united by a shared purpose: to improve the metabolic health and happiness of our members. We believe in empowering every Twin to make a meaningful impact for our members, our clients, and each other, while enjoying a supportive, collaborative work environment.

Twin has been recognized not only for our innovation but also for our culture, including: Innovator of the Year by the Employer Health Innovation Roundtable (EHIR), selected to CB Insights’ Digital Health 150, and named one of Newsweek’s Top Most Loved Workplace® .

With more than $100 million raised in recent funding, including a $53 million Series E round in 2025 led by Maj Invest, and a $50 million investment in 2023 led by Temasek, Twin is scaling rapidly across the U.S. and globally. Backed by leading venture firms like ICONIQ Growth, Sequoia, Sofina, Temasek, and Peak XV, we are building the most impactful digital health company in the world.

Join us as we reinvent the standard of care in metabolic health.

This role is a unique opportunity to build the data foundation behind how Twin proves its value to every partner it serves. You won’t just maintain pipelines; you’ll design the claims data model that powers partner reporting, performance guarantee measurement, and a new partner-facing portal.As the Real World Data Lead, you’ll own Twin’s claims data architecture from end to end. You’ll take partner claims data from its ingested raw form, standardize it to deliver trusted, analytics-ready tables to internal teams and external partners. You’ll also consolidate our existing reporting marts onto this common foundation. This is a highly visible role at the center of how Twin demonstrates outcomes and savings. You’ll collaborate closely with data engineering, application engineering, health economics, and partner-facing teams.

• →Build Twin’s Tuva-based claims data model by designing and implementing the architecture in dbt and Snowflake, from the Tuva Input Layer through Tuva Core and the data marts our reporting depends on.
• →Develop and maintain partner connectors that map each partner’s ingested claims and eligibility data to the Tuva Input Layer. You’ll partner with the ingestion team to define clear data contracts at the handoff between raw and modeled data.
• →Own claims data quality by running structural and logical data quality checks, monitoring each partner data source, and reconciling modeled outputs against partner-reported totals.
• →Consolidate existing reporting marts onto the common data model, retiring duplicated claims logic. You’ll run old and new versions in parallel so current reporting continues uninterrupted during migration.
• →Build the partner portal serving layer with versioned, contract-enforced tables designed for application queries. This includes pre-aggregated models, performance tuning, and freshness commitments that partners can rely on.
• →Enforce partner data isolation and PHI security in Snowflake using role-based access, row access policies, secure views, and masking, so that each partner sees only its own data.
• →Maintain a single source of truth for metrics by ensuring that savings, PMPM, utilization, and outcome measures in the portal match the definitions used for contract measurement. You’ll work closely with health economics and actuarial partners on those definitions.
• →Manage the model lifecycle, including Tuva version upgrades, regression testing, CI/CD, documentation, and change communication to downstream consumers.
• →Other duties as assigned

• Background: Bachelor’s degree in Computer Science, Information Systems, Engineering, or a related field. You bring 6+ years of experience in data or analytics engineering, including 3+ years working directly with healthcare claims data.
• Claims Expertise: Deep familiarity with medical and pharmacy claims and eligibility data, including adjudication, reversals, claim lag, and standard code sets (ICD-10, CPT/HCPCS, NDC, NPI). Experience with payer data formats (837, 835, 834) is a plus.
• dbt Expertise: Extensive experience building and maintaining production dbt projects, including model contracts and versions, testing, and CI. Hands-on experience with the Tuva Project is strongly preferred.
• Snowflake Proficiency: Advanced SQL and Snowflake experience, including query performance tuning, RBAC, row access and masking policies, and warehouse cost management.
• Data Product Mindset: Proven experience delivering data to applications or external customers through stable, versioned interfaces, with a clear sense of what “production-grade” means when a partner is on the other end.
• Collaboration: Proven ability to work cross-functionally with data engineering, application engineering, and analytical teams to define data contracts, metric definitions, and ownership boundaries.
• Innovation & AI Mindset: Demonstrated interest in using AI-assisted development and coding agents to accelerate connector development, testing, and documentation.
• Passion: Twin’s purpose to transform lives by empowering people to reverse, prevent and improve chronic metabolic diseases excites you.
• This hybrid opportunity based out of our New York office. Applicants must be authorized to work for any employer in the U.S. We are unable to sponsor or take over sponsorship of an employment Visa at this time.