Data Scientist, EHR & PMS Integrations

Liine

Raleigh (NC)

Hybrid

USD 110,000 - 150,000

Full time

2 days ago
Be an early applicant
Application generator

Stand out for this role — generate a tailored resume and cover letter in about a minute.

Get past ATS filters

Benefits offered by this job

Generous equity package
4% 401K contribution match
Health, dental and vision insurance
Short and long-term disability
Unlimited PTO

Job summary

Liine, a Raleigh-based software startup, is seeking a Data Scientist to join the Healthcare Data Integrations team. You will profile and transform healthcare data, validate landing quality, and bridge raw vendor data with Liine’s MROI product.

Expect daily SQL/Python work, close collaboration with an Integration Software Engineer, and ownership of data accuracy in a HIPAA-sensitive environment. You’ll contribute to mappings, ingestion pipelines, and data-monitoring tooling, shaping future

Qualifications

  • 5–7 years with production data and experience impacting business decisions.
  • Strong SQL and Python for profiling, validation, and transformation daily.
  • Healthcare data-quality judgment for patient, appointment, encounter, and charge data.
  • Comfort with relational data modeling and linking dimensions and facts.
  • ETL and ingestion experience with file-based, warehouse, or data-lake handoffs.
  • Clear written and verbal communication to explain data problems to vendors and leaders.
  • Ownership and rigor in validating numbers and communicating issues.

Responsibilities

  • Audit new data sources for MROI readiness and provide go/conditional-go/no-go recommendations.
  • Diagnose and resolve data-quality blockers and request fixes from vendors or aggregators.
  • Define normalization and mapping logic to Liine's data model and create stable transforms.
  • Collaborate with production ingestion to turn mappings into repeatable pipelines.
  • Own ongoing data quality with monitoring, reconciliation, and drift-detection checks.
  • Build tooling and templates to automate repetitive audit work for future integrations.
  • Support build vs. buy decisions by evaluating quality, cost, and control.

Skills

5–7 years exp
SQL
Python
Healthcare data quality
Relational data modeling
ETL / data ingestion
Clear communication
Ownership & rigor

Tools

Snowflake
AWS S3

Job description

Sep 23, 2026

Job Overview

Liine is a fast-growing software startup based in downtown Raleigh, NC. Our AI-powered call tracking, marketing analytics and ad optimization platform helps specialty healthcare and dental practices convert more new patient inquiries into appointments. With over $10M in ARR and winner of the 2026 Triangle Business Journal's 50 Best Places to Work, we are on our way to making Liine a core component of every healthcare practice's technology stack.

You will be joining our Healthcare Data Integrations team to help build how patient, appointment, and revenue data gets into Liine. Team responsibilities include:

Direct EHR/PMS integrations — designing and standing up direct connections to systems like ModMed, NextGen, Open Dental, WinOMS/Carestream, and others.

Bespoke MROI audits and ingestion — profiling raw sample data from partner data sources, proving feasibility, and building the ingestion that powers MROI reporting.

Aggregator program management — project-managing integrations that run through third-party data aggregators, and holding those partners accountable to data quality standards.

Build vs. buy evaluation — assessing integration decisions over time based on data quality, cost, and control considerations.

This is a relatively new mandate at Liine, so the team has unusual room to shape its own tooling, standards, and playbooks.

The role:

As the team's Data Scientist, you are the person who looks at a brand-new pile of healthcare data and figures out whether — and how — it can be trusted to drive revenue reporting. You will sit at the intersection of raw vendor data and the Liine MROI product, profiling incoming data, diagnosing quality problems, defining the mappings and transformations that normalize it, and validating that what lands in our dashboards is correct.

You will work hands-on every day in SQL and Python, partner closely with the Integration Software Engineer who builds the production pipelines, and act as Liine's technical counterpart to the data analysts and engineers on the vendor and aggregator side. This is a deep individual contributor role for someone who is energized by messy, real-world healthcare data and takes pride in getting it right.

Our top priorities for this role are data accuracy and security. You will be working with data used to drive millions of dollars of decisions — accuracy and transparency are essential. You will also be handling data protected under HIPAA, which must always be kept private and secure. Security is not an afterthought at Liine, and all candidates should seriously consider the responsibility that comes with this role.

What you'll do:
  • Audit new data sources for MROI readiness. Profile EHR, PMS, and partner data-lake exports for completeness, key coverage, linkage, and revenue-reporting feasibility, then deliver a clear go / conditional-go / no-go recommendation.
  • Diagnose and resolve data-quality blockers. Identify the specific issues that break reporting, such as missing encounter IDs, incomplete charge fields, weak patient matching, or absent creation dates, and convert them into precise requests for vendors or aggregators.
  • Define normalization and mapping logic. Map vendor schemas to Liine's data model and design transformations such as collapsing inconsistent, EMR-specific appointment statuses into stable FHIR-style buckets that hold up across many source systems.
  • Partner on production ingestion. Work with the Integration Software Engineer to turn validated mappings into repeatable pipelines, including file-based and data-lake handoffs.
  • Own ongoing data quality. Build monitoring, reconciliation, and drift-detection checks that keep MROI reporting accurate after go-live.
  • Build the team's tooling and standards. Help turn repeated audit work into reusable tooling, templates, and eventually more automated auditing, so each successive integration is faster than the last.
  • Support build vs. buy decisions. Help assess integration options as the program scales, weighing data quality, cost, and control against partnership and aggregator alternatives.
What you'll bring:
  • 5–7 years with production data. You have worked in data science, data engineering, data quality, or analytics engineering roles where imperfect real-world data directly affects business decisions.
  • Strong SQL and Python. You are fluent in SQL and comfortable using Python, including pandas or equivalent tools, for profiling, validation, and transformation work every day.
  • Healthcare data-quality judgment. You can reason about null rates, key coverage, record linkage, and downstream reporting risk, especially in patient, appointment, encounter, and charge data.
  • Comfort with relational data modeling. You understand entity relationships and joins deeply and can reason about how dimensions and facts (patients, appointments, encounters, charges) should link.
  • ETL and ingestion experience. You have built or closely supported pipelines involving file-based, warehouse, or data-lake handoffs such as CSV, S3, Snowflake, or similar systems.
  • Clear written and verbal communication. You can explain a data problem precisely enough that a vendor's engineer knows exactly what to fix and summarize an audit so a product leader can make a call.
  • Ownership and rigor. You are comfortable being accountable for whether the numbers are right and communicating issues clearly to both technical and product stakeholders.
Nice to have:
  • Experience with healthcare data — EHR/PMS systems, clinical or claims/charge data, or FHIR-based models.
  • Familiarity with specific systems in our world: ModMed, NextGen, Open Dental, WinOMS / Carestream, eClinicalWorks, AdvancedMD, or Athena.
  • Experience working through healthcare data aggregators or middleware platforms.
  • Working knowledge of PHI/HIPAA handling, BAAs, and secure data exchange.
  • Snowflake and AWS (S3, IAM) familiarity, including storage-integration patterns between a partner's warehouse and your buckets.
  • Exposure to marketing-attribution or revenue/ROI analytics.
  • Interest in building internal tooling and pushing toward more automated, repeatable data audits.
How you'll work:

You will report to the Healthcare Data Integrations Team Lead and work in close, day-to-day partnership with the team's Integration Software Engineer. The role also carries a strong dotted-line relationship to Liine's Director of Engineering, who sets technical standards and helps guide the more architectural calls. You will collaborate regularly with Product, Implementation, and Customer Operations, and you will be Liine's hands-on technical point of contact with our integration and aggregator partners.

Perks and benefits include:
  • Generous equity package
  • 4% 401K contribution match
  • Health, dental and vision insurance
  • Short and long-term disability insurance
  • Unlimited PTO
Additional Information:

Candidates who can work out of our downtown Raleigh office are preferred, but we will also consider exceptional remote applications. We work from our downtown Raleigh office on

Mondays, Wednesdays and Fridays, with the option to work remotely on Tuesdays and Thursdays.

We’re building something special and are looking for great people to join our team!

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Machine Learning Engineer
Senior Machine Learning Engineer

Liine • Raleigh (NC)

Hybrid
USD 130,000 - 190,000
Equity
401k match
Health insurance
+5
Healthcare Data Scientist - EHR & PMS Integrations
Healthcare Data Scientist - EHR & PMS Integrations

Liine • Raleigh (NC)

Hybrid
USD 110,000 - 150,000
Generous equity package
4% 401K contribution match
Health, dental and vision insurance
+2
Senior Full Stack EngineerNewHybrid
Senior Full Stack EngineerNewHybrid

SpringTime Ventures • Raleigh (NC)

Hybrid
USD 120,000 - 160,000
Competitive salary
Equity package
4% 401K contribution match
+4
Senior Data Engineer
Senior Data Engineer

HealthLeap • San Francisco (CA)

On-site
USD 175,000 - 275,000
Equity
Healthcare premiums covered
Unlimited PTO 20 days minimum
+1
Senior Data Engineer
Senior Data Engineer

RiseMe • San Francisco (CA)

Hybrid
USD 175,000 - 275,000
Unlimited PTO
401(k) match
Laptop and home office budget
+1
Senior Data Scientist
Senior Data Scientist

Internetwork Expert • United States

Hybrid
USD 140,000 - 190,000
Health care plan
401k retirement plan
Paid time off
+2
Senior/Principal Data Engineer
Senior/Principal Data Engineer

Waymark • United States

On-site
USD 124,000 - 229,000
Stock Options
Work-from-Home Stipend
Comprehensive Medical, Vision and Dental Coverage
+6
Software Engineer
Software Engineer

Stealth-Healthtech-Startup • New York (NY)

Hybrid
USD 140,000 - 210,000
Competitive salary & stock options
Hybrid setup NYC/remote-friendly
Comprehensive health plans
Senior Data Scientist
Senior Data Scientist

DrFirst • Northern (KY)

Hybrid
USD 140,000 - 170,000
Discretionary bonus
Medical, dental, and vision insurance
401K with match
+3
Lead Data Engineer Hybrid Remote, 2 Locations Lead Data Engineer
Lead Data Engineer Hybrid Remote, 2 Locations Lead Data Engineer

Relatient • United States

Hybrid
USD 140,000 - 210,000
Life Insurance (employee & household)
Accident Coverage
Education Reimbursement
+1