Clinical Data Engineer (Remote)

Lucem Health Inc.; North Carolina; Remote; USD 80,000 - 110,000; Full time

Job summary

An innovative healthcare company is seeking a Clinical Data Engineer to bridge clinical data with AI model development. This role is pivotal in ensuring our AI-driven products deliver actionable insights for improved patient care. You'll collaborate closely with engineering and product management teams to analyze data, support product development, and enhance clinical workflows. If you're passionate about leveraging technology to revolutionize healthcare and drive proactive care, this opportunity is perfect for you. Join a forward-thinking team dedicated to making a meaningful impact in diagnostic medicine and patient outcomes.

Qualifications

• 4+ years of software development experience required.
• Strong knowledge of cloud computing and data analytics.
• Excellent communication skills for diverse teams.

Responsibilities

• Collaborate with engineering teams for data integration.
• Perform validation of data outputs for clinical accuracy.
• Research disease areas and document clinical definitions.

Skills

Software Development

Data Analytics

Cloud Computing

Clinical Workflows

Communication Skills

Education

Bachelor’s Degree in Computer Science

Relevant Experience in Software Development

Tools

Jira

Confluence

Smartsheet

SharePoint

Microsoft Office

ChatGPT

Gemini

CoPilot

SQL

Python

Json

AWS

Azure

All of Us

PySpark

Job description

Who We Are

Lucem Health’s mission is to help revolutionize diagnostic medicine. With our partner and investor Mayo Clinic, we will enable and support earlier disease detection, increased diagnostic efficiency, and greater patient agency.

“Lucem” is a Latin word meaning “bring the light of day.” Our platform helps diagnostic medicine-focused AI and machine learning algorithms “see the light of day” by connecting these algorithms with patient telemetry data and delivering algorithm-generated insights into clinical workflows… to the right stakeholder, in the right place, in the right context, at the right time.

Founded in 2021 through a collaboration between Mayo Clinic, Rally Ventures, and Commure (a General Catalyst company), Lucem Health is on a mission to revolutionize healthcare delivery with the practical application of clinical AI. We empower healthcare organizations to detect diseases at an earlier stage and identify patients who are undiagnosed, ultimately improving outcomes and optimizing limited clinical resources. We envision a future where proactive care enables problems to be detected before they become life-threatening and patients get world-class care, everywhere.

We are focused on helping providers deliver more proactive care by accelerating diagnosis and treatment. To do so, we’ve built a platform that connects patient data from varied sources with powerful, clinically focused AI algorithms and other advanced tools. We deliver the insights generated by these tools seamlessly into clinical workflow: to the right stakeholder, in the right place, in the right context, at the right time. We help clinicians and other stakeholders engage with, understand, trust, and adopt these tools so they see them as valuable partners that support better care and outcomes for patients.

We leverage this platform – Lucem Health Reveal – to deliver AI-enabled solutions, targeted at specific diseases, that deliver distinct and measurable clinical value propositions and financial benefits to our provider customers.

About our Products - Reveal, Disease Insights, and AI Model Development:

Lucem Health’s Reveal solutions leverage clinical AI models to identify patients at a higher risk for life-threatening or chronic diseases—even in the absence of traditional indicators such as symptoms or screening results. By detecting subtle patterns in clinical data, Reveal solutions enhance early detection and treatment acceleration, driving proactive care strategies and meaningful clinical and financial yield all while optimizing scarce care delivery resources.

Disease Insights is an advanced analytics platform designed to help our life science partners refine provider outreach, optimize reimbursement strategies, and capture a larger share of a growing market. It leverages real-world patient data to give insight into diagnostic and treatment pathways across populations of patients.

The AI models created by our data science team serve as the engines behind our Reveal solutions. This team develops and refines these advanced clinical AI models to identify patients at highest risk of disease.

As a Clinical Data Engineer, you will act as a bridge between clinical data, AI model development, and product strategy, ensuring that the Disease Insights and Reveal products provide accurate, impactful, and actionable insights for our customers and partners.

Position Summary

Product development is at the center of what we do. By building great products that “do the jobs” our customers need and expect them to do, we will go a long way to fulfilling our mission. If you are passionate about creating the foundation for highly differentiated products that delight customers and win in the market, our Clinical Data Engineer role may be for you.

As a Clinical Data Engineer, you will play a critical technical role in analyzing the data used by the Disease Insights product, working in close collaboration with Engineering and Product Management. Through clinical research, you will compile requirements for Data Scientists and Engineers, supporting the development of Disease Insights, Reveal, and other AI-driven solutions. The goal is to ensure these tools effectively address customer needs and provide meaningful clinical insights that drive market impact.

This position is remote. As a remote workforce that meets face-to-face frequently to do collaborative work, this position will require occasional travel to Raleigh or Charlotte, North Carolina, or to other cities where there is, or will be, a critical mass of Lucem employees.

Key Responsibilities:

• Collaborate with engineering teams to ensure accurate integration of data sources (e.g., EMR data, claims data, etc.).
• Maintain and update medical coding crosswalk mappings for use within the organization.
• Gather insights on patient pathways, physician workflows, and decision-making criteria for diagnosing and managing the target disease.
• Understand and document the clinical definition of the diseases being supported and become a subject matter expert in those diseases through research.
• Perform validation of data outputs to ensure accuracy and relevance to clinical scenarios.
• Troubleshoot and resolve issues related to data inaccuracies or inconsistencies.
• Transformation (EMR, FHIR and OMOP Experience)
  • Design, test and develop software to meet those needs.
• Data Analysis across multiple EMRs
• Healthcare Data Set Analysis & Discovery
  • Disease-specific clinical analysis of relevant EMR data
• Coordination of data needs across business units

Qualifications:

• A Bachelor’s Degree in computer science, information systems, engineering or related field, or relevant experience in the Software Development field.
• 4+ years of software development experience.
• Strong knowledge of cloud computing concepts and experience working with one of the following cloud providers: GCP (preference), AWS, Azure
• Technical Expertise: Strong background in data analytics, clinical workflows, or healthcare technology systems. Familiarity with EMR data, clinical terminologies (e.g., ICD-10, LOINC, NDC, CPT), and diagnostic criteria. Ability to develop software using Go, SQL, Python or other programming languages.
• Domain Knowledge: The ability to research targeted disease areas, including diagnosis processes, treatment pathways, and key laboratory and procedure tests relevant to the disease.
• Communication Skills: Excellent ability to collaborate with diverse teams and present findings to technical and non-technical audiences.
• Key Tools: Jira, Confluence, Smartsheet, SharePoint, Microsoft Office, ChatGPT, Gemini, CoPilot, SQL, Python, Json, AWS, Azure, All of Us, and PySpark