Sara Pournourbakhsh - Sr. Data Scientist
Boyds, MD 443-***-**** *********@*****.***
LinkedIn Kaggle GitHub
EDUCATION & CERTIFICATIONS
M.S. Data Science & Machine Learning Engineering, UMBC - Present (GPA: 3.85) Professional Certificate in Data Science & Business Analytics, UMD - 2024 M.S. & B.S. in Agriculture Engineering, Azad University Databricks Accredited Generative AI Fundamentals (2024) Apache Spark (TM) Programming with Databricks (2023) TECHNICAL SKILLS
Languages & Libraries: Python, PySpark, SQL, R, Scikit-learn Big Data & Cloud: Databricks, Azure Data Factory, AWS, Hadoop, Parquet ML & AI: Regression, Random Forest, Gradient Boosting, SHAP, SVM, MLOps Visualization: Tableau, Power BI, Matplotlib, Seaborn Tools: Git, Docker, Jupyter, Azure DevOps, CI/CD Pipelines EXPERIENCE
Independent Data Science Consultant Remote 2022-2024
- Designed and deployed ML models in healthcare and fintech sectors using Python, PySpark, and Databricks.
- Built automated data pipelines using Azure Data Factory and deployed end-to-end models with CI/CD.
- Applied SHAP and LIME for model interpretability and stakeholder communication.
- Collaborated across teams to streamline data access, ensure governance, and improve tooling. Data Engineer / Scientist Iranian E-Pack Path 2018-2022
- Led development of data dashboards and ML models to identify business opportunities.
- Automated data workflows with Python and improved data access with cloud solutions.
- Acted as internal consultant to connect data engineering with strategic analytics teams. Data Analyst Pasargad Electronic 2014-2018
- Built predictive models for EMR data, enabling clinical teams to improve decisions.
- Supported advanced analytics using SQL, Python notebooks, and visualization tools. PROJECTS
Heart Disease Prediction:
- Logistic regression and gradient boosting models with SHAP interpretability. Customer Churn Prediction:
- Deep learning and logistic regression models with class balancing and business metrics. Sara Pournourbakhsh - Sr. Data Scientist
Health Data Pipeline on Databricks:
- Developed scalable PySpark ingestion pipeline using Azure + Databricks with Parquet optimization. HIGHLIGHTS
- 8+ years in data science, ML, and analytics across healthcare, finance, and telecom.
- Proven ability to build and deploy ML models in MLOps and cloud-native environments.
- Hands-on experience with Azure Data Factory, Databricks, and enterprise ML pipelines.