Twinkle Inamdar

Designed and maintained enterprise-grade ETL/ELT pipelines processing patient, provider, and claims data for a major insurance client using Airflow and dbt. Owned data warehouse architecture on Snowflake and AWS Redshift including schema design, partitioning, and performance tuning. Implemented GDPR-aligned governance frameworks covering PII classification, lineage tracking, and access controls. Leveraged Claude and OpenAI APIs to accelerate pipeline development.

Built SQL and Python-based data profiling and validation frameworks across 20+ enterprise datasets supporting regulatory and financial reporting. Engineered complex pipelines integrating 6+ relational datasets for financial reporting and workforce analytics. Designed source-to-target mappings and ER diagrams to support enterprise data architecture and lineage tracking. Supported data governance initiatives aligned with regulatory requirements.

Built ML models using Scikit-learn to forecast COVID-related logistics demand. Deployed real-time supply chain tracking application on AWS. Performed feature engineering and model evaluation to improve predictive accuracy. Created dashboards to communicate model insights to non-technical stakeholders.

Built ETL pipelines using SQL and Python to process and transform enterprise operational data. Developed Tableau dashboards to visualize KPIs and operational metrics. Conducted analysis identifying process inefficiencies contributing to a 7% improvement in operational profitability.

Analyzed web traffic, acquisition funnels, and user behavior using Google Analytics and Tableau. Developed performance dashboards tracking vendor profitability and customer engagement metrics. Identified key growth drivers and optimization opportunities to improve conversion rates and business performance.