Navya A.

Experience

1. Ai Ml Data Engineer - Data Insights

   AT&T

   Jan 2023 — Present · Dallas, TX, US

   AI/ML Data Engineer @ AT & TAt AT & T, I built and scaled advanced data platforms powering real-time insights, predictive analytics, and ML automation across enterprise teams. I led the development of streaming and batch pipelines on AWS using services like Glue, Kinesis, Lambda, and EMR—reducing data latency by 50% and enabling near-instant decision-making.I implemented a robust Snowflake Medallion Architecture to streamline raw-to-curated transformations, improving query performance by 4x and supporting multiple LOBs. By migrating 6,900+ legacy sources and applying fuzzy logic in PySpark, I boosted match accuracy by 15% and eliminated duplicates—directly enhancing sales funnel efficiency.On the ML side, I engineered a SageMaker-powered churn prediction pipeline with schema evolution handling, model monitoring, and alerting via CloudWatch and Lambda achieving 30% cost savings and high model uptime. I also delivered dbt-based modular ELT pipelines, normalized nested JSON, and enforced GDPR/CCPA compliance via Lake Formation and Macie.My work extended to building CI/CD automation (GitHub Actions, Docker, Pytest), visual analytics (Tableau, Athena), and cost-optimized architectures (S3 + Spectrum, Redshift WLM). Every piece of the pipeline—from ingestion to model to visualization—was built with performance, reliability, and future scalability in mind.Re-platformed Azure Data Factory pipelines into Microsoft Fabric Data Factory (ERP→Lakehouse→Power BI), with several pipelines already in production.Resolved Fabric migration issues including governance gaps (Purview lineage), schema drift from ERP feeds, and CI/CD PySpark transformation fixes.

Education

• University of Wisconsin-Milwaukee

  Master's degree, Information Technology