Data Scientist

We are seeking a Data Scientist - ML with hands-on experience in building and deploying data-driven solutions.
You will work closely with cross-functional teams to extract insights, develop machine learning models, and deploy scalable analytics solutions across various cloud platforms. As a Data Scientist - ML, you’ll play a key role in harnessing data to drive better outcomes, improve performance, and enhance the lives of those served by our clients.

Key Responsibilities:

- Design and implement predictive models and machine learning algorithms to solve healthcare-specific challenges
- Analyze large, complex healthcare datasets including electronic health records (EHR) and claims data
- Develop statistical models for patient risk stratification, treatment optimization, population health management, and revenue cycle optimization
- Build models for clinical decision support, patient outcome prediction, care quality improvement, and revenue cycle optimization
- Create and maintain automated data pipelines for real-time analytics and reporting
- Work with healthcare data standards (HL7 FHIR, ICD-10, CPT, SNOMED CT) and ensure regulatory compliance
- Develop and deploy models in cloud environments while creating visualizations for stakeholders
- Present findings and recommendations to cross-functional teams including clinicians, product managers, and executives

Qualifications Required:

- At least 2 years of hands-on experience in data science, analytics, or machine learning roles
- Demonstrated experience working with large datasets and statistical modeling
- Proficiency in Python, Python Anaconda library for data analysis and machine learning
- Experience with SQL and database management systems
- Experience with ML and Deep Learning frameworks using one or more of TensorFlow, PyTorch, Keras, scikit-learn, MLFlow, Kubeflow.
- Familiarity with data visualization tools such as Tableau, Power BI, matplotlib, ggplot2
- Experience with version control systems (Git) and collaborative development practices
- Strong foundation in statistics, hypothesis testing, and experimental design
- Experience with supervised and unsupervised learning techniques
- Knowledge of data preprocessing, feature engineering, and model validation
- Understanding of A/B testing and causal inference methods
- Experience with cloud platforms and big data technologies such as Spark, Hadoop

What You’ll Need to Be Successful (Required Skills):

- Advanced Algorithm Implementation: At least 1-2 years of experience implementing and optimizing machine learning algorithms from scratch, including deep understanding of algorithmic complexity, hyperparameter tuning, and performance optimization techniques
- Model Pipeline Development: Proficiency in designing and building end-to-end ML pipelines including data ingestion, feature engineering, model training, validation, and deployment using tools like Apache Airflow, Kubeflow, or MLflow
- Cross-Validation and Model Selection: Experience with advanced model validation techniques including k-fold cross-validation, stratified sampling, time series validation, and ensemble methods for robust model selection and performance estimation
- Feature Engineering and Selection: Deep knowledge of feature engineering techniques including dimensionality reduction (PCA, t-SNE, UMAP), feature selection methods, and automated feature engineering approaches for improving model performance
- Model Interpretability and Explainability: Experience with model interpretation techniques such as SHAP, LIME, permutation importance, and other explainable AI methods to understand and communicate model decision-making processes
- Deep Learning Architectures: Familiarity with designing and implementing custom neural network architectures including CNNs, RNNs, Transformers, and experience with transfer learning and model fine-tuning techniques
- MLOps and Model Monitoring: Understanding of machine learning operations including automated model retraining, drift detection, A/B testing for ML models, and continuous integration/continuous deployment (CI/CD) practices for ML systems

Education/ Certifications:

- Bachelor’s or master’s degree in computer science, Data Science, Statistics, Engineering, or a related field.

Preferred Skills:

- At least 1 year of experience working with healthcare data or in healthcare IT environments
- Familiarity with electronic health record (EHR) systems and healthcare workflows
- Understanding of healthcare data privacy regulations (HIPAA, HITECH)
- Knowledge of clinical data standards and interoperability frameworks
- Knowledge of MLOps practices and model deployment pipelines
- Familiarity with natural language processing for clinical text analysis
- Experience with time series analysis for patient monitoring data

Why Join Us?

At Netsmart you’ll work on exciting challenges that shape the future of healthcare.

You’ll have the opportunity to:

- Collaborate with talented professionals passionate