Financial Data Scientist Jobs in Arizona (NOW HIRING)

Savas Software/Lifekind Health is seeking a technically strong, impact-driven Data Scientist with experience building ML-based predictive products and advanced analytics (including LLM based) in real-world environments. In this role, you will work with diverse and complex healthcare datasets—EHR, scheduling, billing, claims, structured & unstructured clinical data—to design, train, and deploy machine learning models that directly influence patient care, operational performance, and clinical efficiency.

This is a high-ownership, hands-on role where you’ll help shape our intelligent data platform, build production-ready features, experiment with models, and collaborate with engineering teams to deploy AI products. If you enjoy solving messy, high-impact healthcare problems using AI, this role is for you.

This is not a remote position.  You must live in the Scottsdale, AZ area and work in our office 3 days per week.  Relocation assistance is not available.  Visa sponsorship is not available.

Our mission is to bring care that’s whole, human, and healing. Blending medical, behavioral, and lifestyle support into a single plan because restoring life takes more than a prescription.

Savas Software is a pioneering healthcare technology company dedicated to transforming clinical operations through innovative, integrated software solutions. Our mission is to empower healthcare organizations with tools that streamline workflows, enhance patient care, and ensure operational continuity. Through a unified approach to development, support, architecture, and enablement, we help clinics focus on what matters most—patient outcomes.

Machine Learning & Predictive Analytics:

• Develop and deploy AI/ML models that power key products such as:

• Procedure Appropriateness
• Patient no-show prediction
• Appointment optimization
• Clinical risk stratification
• Patient adherence forecasting
• Providerutilizationand throughput prediction

• Perform feature engineering using clinical, operational, and financial data
• Experiment with algorithms (tree-based models, GLMs, ensemble methods, NLP, deep learning whereappropriate)
• Evaluate models using rigorous statistical and ML performance metrics
• Collaborate with ML Engineering to productionize models on Azure

Technical Environment (Azure AI/ML & Analytics):

You’ll work within a modern AI/ML and analytics stack, including:

• LLMs:Open AI, Anthropic Claude
• Core Languages:Python, SQL
• Libraries & Frameworks:Scikit-learn,XGBoost,LightGBM, Pandas, NumPy, NLP libraries
• Visualization:Power BI, Plotly, Matplotlib, Seaborn

Data Analysis & Insights:

• Conduct exploratory data analysis (EDA) on EHR, scheduling, billing, and procedural data to uncover trends, biases, and quality issues
• Translate clinical guidelines and workflows into computable, data-driven logic
• Generate actionable insights that drive clinical and operational decision-making

 Data & Feature Pipelines:

• Transform raw healthcare data into modeling-ready datasets (structured + unstructured)
• Implement data validation, quality checks, and scalable transformation logic
• Collaborate with Data Engineering to ensure high-quality, well-governed data pipelines

 LLMs, NLP & Unstructured Data (Nice-to-Have but Valuable):

• Work with LLMs (Open AI, Anthropic Claude) to research and conceptualize recommendations
• Apply basic NLP techniques to extractsignalfrom clinical notes and operational text
• Explore entity extraction, rule-based labeling, embedding-based features, etc.

 Visualizations & Storytelling:

• Create dashboards and data visualizations using Power BI or Python to communicate insights
• Present findings and recommendations to clinicians, operations leaders, and executives

What Success Looks Like:

• Production-ready ML models that drive measurable improvements in clinical operations
• High-quality datasets, features, and reproducible pipelinespoweringour AI platform
• Actionable insights that influence patient outcomes and reduce operational friction
• Ability to independently drive complex data projects end-to-end with minimal supervision

Our Ideal Candidate will have the following qualifications:

• 2 or more years of experience in data science, machine learning, or applied analytics
• Strong Python + advanced SQL skills for data manipulation, modeling, and EDA
• Experience developing and evaluating ML models in real-world environments
• Experience with healthcare datasets (EHR, claims, clinical notes, billing, scheduling) is a strong advantage
• Familiarity with HIPAA, PHI handling, and healthcare data governance
• Strong understanding of feature engineering, statistical methods, and model validation
• Ability to clearly communicate technical concepts to non-technical stakeholders
• Exposure to Prompt Engineering and working with LLMs (Open AI, Anthropic Claude) preferred