Data Science Engineer

Description

nimble Solutions is seeking a Data Science Engineer to build and operationalize data products that improve healthcare revenue cycle performance. This role will work with data from the company’s warehouse and business applications to develop trusted analytics, predictive models, and decision-support tools for RCM teams. The successful candidate combines strong data engineering skills with applied data science expertise and can translate operational questions into reliable, measurable solutions. 

Microsoft Fabric engineering experience is a must. Most data for this role will come from nimble’s new data warehouse, so the engineer must be able to work effectively with Fabric-based data pipelines, lakehouse/warehouse patterns, transformations, and analytics workflows. 

Key Responsibilities 

• Build, maintain, and optimize data ingestion and transformation pipelines in Microsoft Fabric. 
• Develop and support lakehouse and warehouse data structures, curated data models, and reusable datasets for analytics and data science. 
• Integrate data from the enterprise warehouse and relevant RCM, financial, operational, and third-party sources, subject to approved access and data governance. 
• Profile, validate, reconcile, and document data; investigate quality issues and work with source systems and business teams to resolve them. 
• Apply statistical analysis and machine-learning methods to practical RCM problems, such as denial patterns, accounts receivable prioritization, payment and claims trends, workflow forecasting, and operational capacity planning. 
• Develop reproducible feature engineering, model training, evaluation, and scoring workflows; select metrics that reflect business outcomes and model risk. 
• Deploy, monitor, and maintain data products and models in collaboration with data engineering, analytics, applications, and business teams. 
• Create clear visualizations, dashboards, and written findings that help RCM stakeholders understand performance, drivers, and recommended actions. 
• Partner with subject-matter experts to define use cases, success measures, requirements, and appropriate human review for decision-support outputs. 
• Follow data governance, privacy, security, and responsible AI practices, especially when working with sensitive healthcare or financial information. 
• Maintain technical documentation, lineage, testing, and support procedures for pipelines, datasets, and models. 

Requirements

  Required Qualifications 

• Bachelor’s degree in Data Science, Computer Science, Statistics, Engineering, Mathematics, or a related field; equivalent practical experience may be considered. 
• Demonstrated hands-on experience engineering data solutions in Microsoft Fabric. This is a required qualification, not a preferred skill. 
• Strong SQL skills and experience with Python for data preparation, analysis, and model development. 
• Experience building production-quality data pipelines, transformations, and analytical data models. 
• Working knowledge of data warehousing, dimensional modeling, data quality testing, and pipeline monitoring. 
• Experience applying statistical or machine-learning techniques to real-world business problems, including model evaluation and communication limitations. 
• Ability to explain technical findings to both technical teams and business stakeholders. 
• Strong problem-solving, documentation, collaboration, and prioritization skills. 

Preferred Qualifications 

• Experience in healthcare revenue cycle management, medical billing, claims, denials, payment posting, coding, or accounts receivable. 
• Familiarity with healthcare data and relevant privacy and security expectations. 
• Experience with Power BI and semantic models, including preparing governed datasets for reporting. 
• Experience with source control, automated testing, CI/CD, and production monitoring for data solutions. 
• Experience with model deployment, monitoring, drift evaluation, and responsible use of predictive outputs. 
• Familiarity with Microsoft Azure data services and integration patterns that complement Microsoft Fabric. 

Success Measures 

• Reliable, well-documented Fabric pipelines and curated datasets that meet agreed freshness and quality expectations. 
• Reduced time spent on manual data preparation and reconciliation for RCM reporting and analysis. 
• Analytics and models that are adopted by stakeholders and demonstrate measurable operational value. 
• Clear ownership, monitoring, and support processes for production of data products. 
• Consistent adherence to data governance, privacy, security, and responsible AI requirements. 

Working Relationships The role works closely with data engineering, analytics, business intelligence, IT, application teams, and RCM operational stakeholders. It collaborates with subject-matter experts to ensure data products address real workflows and produce interpretable, actionable results. Position Details 

• Department: Data & Analytics / Data Science 
• Reports to: Eric Pidgeon, Director Data & AI 
• Location: Hyderabad 
• Employment type: FULL TIME