Open to opportunities

Shriya Thabe User

@shriyathabeuser

Message

Data analyst building scalable ETL pipelines and ML-driven document processing.

India

Message

What I'm looking for

I’m looking for a role where I can own end-to-end data pipelines—ETL, validation, and production automation—while building ML-powered analytics and dashboards that improve business decisions with clean, well-documented data.

I’m a Data Analyst focused on turning raw data into reliable, decision-ready products. I’ve engineered scalable ETL and data validation pipelines with PySpark and SQL, loading structured datasets into MySQL and Snowflake to power client dashboards and business reporting.

I also build automation-first workflows, from ML document-processing pipelines using OpenCV and OCR-based feature extraction to re-architecting ingestion pipelines with scraper-based retrieval and performance benchmarking. Alongside production troubleshooting and documentation, I create impactful analytics experiences—automated reporting, R Shiny dashboards, and BI work in Power BI and Tableau—supported by classical ML, simulation-driven experimentation, and rigorous data integrity practices.

Experience

Work history, roles, and key accomplishments

Current

Data Analyst

Current

India DataHub

Oct 2025 - Present (9 months)

Engineered scalable ETL and data validation pipelines in PySpark and SQL, loading structured datasets into MySQL and Snowflake to support client dashboards and business reporting. Built an OpenCV and OCR-based document-processing ML pipeline and re-architected ingestion workflows to improve MySQL query execution and dashboard responsiveness.

Python Pyspark SQL ETL Data Validation MySQL Snowflake OpenCV Document Processing Machine Learning Pipelines Workflows Git

Computational Data Science Intern

MuSigmas SL Consultants

Jan 2025 - Aug 2025 (7 months)

Implemented and tuned classical ML models across simulation runs, improving experimental design efficiency via hyperparameter optimization and statistical evaluation. Built a production-ready R Shiny dashboard with GLMMs and survival analysis and automated ETL pipelines for model evaluation cycles.

R C SQL Docker Shiny Shiny Server Survival Analysis ETL Quarto Git

Research Assistant

The Centre for Applied Social Sciences

Jun 2023 - Dec 2023 (6 months)

Developed an IPSAS survey using global datasets and tools such as SQL and R, ensuring data integrity and methodological rigor. Applied classical ML (K-Means clustering) to analyze survey responses and improve data quality.

SQL R Power BI Python Excel