Analytics Data Scientist

RadNet•UNAVAILABLE, OH

19h

About The Position

Artificial Intelligence; Advanced Technology; The very best in patient care. With decades of expertise, RadNet is Leading Radiology Forward. With dynamic cross-training and advancement opportunities in a team-focused environment, the core of RadNet’s success is its people with the commitment to a better healthcare experience. When you join RadNet as an Analytics Data Scientist, you will be joining a dedicated team of professionals who deliver quality, value, and access in the 21st century and align all stakeholders- patients, providers, payors, and regulators to achieve the best clinical outcomes.

Requirements

Master’s or Ph.D. in Data Science, Statistics, Computer Science, Mathematics, or related quantitative field; or Bachelor’s with equivalent experience
3+ years of experience in data science, machine learning, or advanced analytics roles
Strong proficiency in Python and data science libraries (pandas, NumPy, scikit-learn, statsmodels)
Experience with machine learning frameworks (PyTorch, TensorFlow, XGBoost, LightGBM)
Solid foundation in statistics including regression, hypothesis testing, experimental design, and time series analysis
Proficiency in SQL for data extraction and manipulation
Experience with data visualization tools (Matplotlib, Seaborn, Plotly, or BI tools)
Excellent communication skills with ability to explain complex analyses to non-technical stakeholders

Nice To Haves

Experience with cloud ML platforms (GCP Vertex AI, AWS SageMaker, Azure ML)
Knowledge of MLOps practices and model deployment pipelines
Healthcare analytics experience including clinical, operational, or revenue cycle domains
Experience with causal inference, Bayesian methods, or optimization techniques
Familiarity with LLMs, NLP, or generative AI applications
Experience with big data technologies (Spark, BigQuery, Databricks)
Track record of deploying models that delivered measurable business impact

Responsibilities

Develop analytical models that drive business outcomes: Design and build predictive models for forecasting, demand planning, and capacity optimization. Develop risk and anomaly detection systems for operational and clinical metrics. Create scenario analysis and "what-if" models to support strategic decision-making. Build decision-scoring frameworks that quantify trade-offs and recommend actions. Translate business problems into analytical frameworks with measurable outcomes.
Build, validate, and deploy ML models as enterprise assets: Develop feature engineering pipelines using governed data from the Gold Layer. Train, validate, and evaluate machine learning models using appropriate techniques and frameworks. Implement model monitoring for drift, bias, and performance degradation. Create model documentation including methodology, assumptions, limitations, and explainability. Partner with AI Engineers to deploy models into production environments.
Apply rigorous analytical methods to answer business questions: Conduct exploratory data analysis to identify patterns, trends, and insights. Apply statistical methods (regression, hypothesis testing, time series analysis) to validate findings. Design and analyze experiments (A/B tests, randomized trials) to measure intervention impacts. Quantify uncertainty and communicate confidence levels in analytical outputs. Stay current with advances in data science, ML, and AI methodologies.
Measure and optimize the impact of AI initiatives: Define metrics and KPIs to measure AI model effectiveness and business impact. Track and report on model performance in production environments. Evaluate AI outputs for accuracy, bias, and fitness for purpose. Provide feedback to improve AI systems based on real-world performance. Support responsible AI practices including fairness testing and transparency.
Partner with business teams to deliver analytical value: Collaborate with business stakeholders to understand problems and translate them into analytical projects. Present findings and recommendations to technical and non-technical audiences. Create visualizations and narratives that make complex analyses accessible and actionable. Partner with BI teams to operationalize analytical insights into dashboards and reports. Coach and mentor analysts on statistical thinking and advanced analytical techniques.