Chirag Shinde

Graduate Assistant @ University of Illinois Chicago

About

Data Engineer specializing in building scalable data pipelines and modern data platforms that power analytics and machine learning systems. Experienced in designing ETL workflows, distributed data processing with Spark/PySpark, and implementing robust data architectures to transform large-scale data into analytics- and model-ready datasets. Strong foundation in SQL, data modeling, and data quality engineering, with hands-on exposure to AI/ML systems, time-series forecasting, and Generative AI (RAG) solutions to drive data-driven decision-making and production-grade outcomes.

Country

United States

City

Chicago

Industry

Computer Software

Skill

Data Pipeline Orchestration, PySparks, Delta Lake, Data Governance, Unity Catalog, Data Modeling, Computer Vision, PyTorch, Optical Character Recognition (OCR), TensorFlow, OpenCV, Natural Language Processing (NLP), Image Processing, Data Visualization, Data Analytics, Python (Programming Language), Machine Learning

Experience

Graduate Assistant

University of Illinois Chicago

2025-9 - Present · 1 yr 1 mo

Chicago, Illinois, United States

I design data pipelines and AI-enabled workflows to support research analytics and large-scale data processing initiatives. • Built automated ETL and LLM-powered extraction workflows that reduced manual research effort by 60%, transforming unstructured web data into analytics-ready datasets. • Developed PySpark preprocessing and data validation frameworks with governance controls, improving dataset reliability for ML and statistical research. • Structured research datasets for scalable querying and Power BI analytics, enabling faster insights for faculty teams.

Data Engineer

M.S Engineers

2023-5 - 2024-7 · 1 yr 3 mos

Pune

Worked on building scalable data platforms and ML-supporting pipelines for business analytics. • Improved large-scale data processing efficiency by 30% by building distributed ETL pipelines and modern data architectures for analytics workloads. • Increased forecast precision by 15% by engineering ingestion and transformation pipelines delivering clean time-series data to production ML models. • Designed dimensional datasets and data marts to support scalable BI reporting and KPI tracking. • Implemented CI/CD and data quality frameworks to improve deployment efficiency and production data reliability.