Data Engineer / Machine Learning Engineer

About the job

Role Overview We are looking for a highly skilled Freelance Data Engineer / Machine Learning Engineer to build an end-to-end data pipeline and predictive analytics system focused on life expectancy modeling using public health and socio-economic data. The ideal candidate should have strong experience in data engineering, big data processing, and machine learning, with the ability to work on real-world datasets and derive actionable insights. Key Responsibilities Data Engineering • Build scalable data pipelines using Python, SQL, and Apache Spark • Ingest data from APIs and public datasets (Census, healthcare, etc.) • Design multi-layer architecture: • Bronze (raw data) • Silver (cleaned data) • Gold (aggregated/feature-ready data) • Perform data transformation, joins, and aggregation at regional/community level Feature Engineering • Develop key health indicators such as: • Mortality rates • Poverty & unemployment rates • Healthcare provider density • Food accessibility metrics • Build composite indices like: • Economic Hardship Index • Health Access Index Machine Learning • Develop predictive models using scikit-learn (Random Forest, Regression) • Evaluate models using: • R² Score • RMSE • Perform feature importance analysis to identify key drivers of life expectancy Simulation & Insights • Build an interactive Life Expectancy Simulator • Enable scenario-based analysis (e.g., impact of poverty reduction, healthcare improvements) • Provide recommendations for policy and intervention strategies Visualization & Reporting • Create dashboards using Power BI and Streamlit • Develop geospatial visualizations using Folium • Highlight disparities across communities and generate insights reports Required Skills & Experience • Strong experience in: • Python, SQL • Data Engineering & ETL pipelines • Big Data tools (Spark, Databricks) • Hands-on experience with: • Machine Learning (scikit-learn) • Feature engineering & model evaluation • Experience working with: • Public datasets / APIs • Data modeling & transformations • Good understanding of: • Data pipelines (Bronze/Silver/Gold architecture) • Statistical analysis and predictive modeling Nice to Have • Experience in public health / healthcare analytics • Knowledge of geospatial data analysis • Experience building interactive dashboards or simulators • Exposure to cloud platforms (AWS / Azure / GCP