Data Science Intern / May, 2025 — August, 2025

Drove a 75% reduction in vendor risk review effort by designing a Python and LangGraph analytics pipeline that standardized risk scoring and shortened client decision cycles. Accelerated executive decision making by 40% by building Power BI dashboards that tracked compliance KPIs, cohorts, and segment level trends to balance eligibility, risk exposure, and growth transformation across products. Fixed fragmented, inconsistent, multi-source data by standardizing schemas, building reliable multi-table SQL joins, and implementing validation and reconciliation checks, reducing reporting errors by 25% for executive and product dashboards. Increased model driven risk classification accuracy by 20% by validating multimodal analytics across text, image, and structured datasets to support scalable eligibility assessments. Accelerated analytics delivery by 40% by implementing CICD pipelines using Docker and GitHub Actions, ensuring reproducible and production ready analytics assets.

Data Analyst / May, 2021 — May, 2024

Designed and maintained Python and SQL based ETL pipelines to ingest, transform, and validate data from multiple source systems into a unified analytics layer, improving metrics across dashboards and turnaround time by 30%. Reduced API latency by 20% by engineering backend analytics services and REST APIs integrated with relational databases, supporting product and finance reporting. Identified performance trends and anomalies across large relational datasets using exploratory and statistical analysis, forecasting targeted operational improvements and prioritization decisions. Improved data accuracy and consistency across enterprise reports by implementing SQL based validation checks and reconciliation logic, reducing downstream reporting discrepancies by 25%. Elevated team delivery quality by mentoring 10+ junior engineers on analytics engineering, communication skills, and code review best practices.