Projects

Architected GCP pipeline with Google Gemini multimodal LLM to process 10M+ PDFs for national survey sampling in India.

Migrating data pipelines to Databricks, standardizing datasets using SDMX frameworks, building GAFS Dashboard for food security.

Led Redshift architecture ingesting terabytes of clickstream data for India's National Data Analytics Platform.

Automated raw data transformation workflows for Malawi government's Social Cash Transfer Programme monitoring.

Built scalable data pipelines to expand government benefit access to 3M+ workers with Spark-based eligibility algorithms.

Developed FastAPI-based backend for Ask-Me-Anything chatbot with SQL data models for South African nonprofit.

Created monitoring system for analyzing daycare quality in Kenya using digital data collection and GCP BigQuery.

Optimized MOSAIKS grid sampling with Dask on Azure Kubernetes Service for global satellite image analysis.

Created serverless architecture for mismatch reporting across government data collection levels.

Automated end-to-end testing and data validation for Australian insurance groups using Azure DevOps.

Built HIPAA-compliant patient data systems with statistical metrics and trend analysis for US healthcare groups.

Developed end-to-end regression testing suite and automated surveyor email notifications pipeline.