Pratik Bharuka

Associate Data Engineer specializing in enterprise-scale Databricks Lakehouse platforms, scalable ETL pipelines, and secure data engineering solutions. Experienced in building production-ready solutions using PySpark, Delta Lake, Unity Catalog, and automated CI/CD deployments with Databricks Asset Bundles and GitHub Actions. Contributing to enterprise retail analytics through Causal Inference, XGBoost, and production-grade Generative AI solutions that improve business decision-making and operational efficiency.

Associate Data Engineer at V4C.ai (2025-12 – Present)

• Currently contributing as an Associate Data Scientist (ADS) on a live retail analytics engagement for a Global Coffee Retail Chain, delivering solutions for retail site selection, store performance diagnostics, and marketing effectiveness.
• Developing and evaluating Causal Inference and XGBoost models to quantify business drivers and support strategic decision-making across retail analytics use cases.
• Built and deployed a production-ready RAG assistant using LangChain, LangGraph, ChromaDB, OpenAI, and Slack APIs, reducing enterprise policy lookup time from approximately 10–15 minutes to under one minute by centralizing InfoSec knowledge into a vector database.
• Engineered the end-to-end retrieval pipeline with semantic chunking, vector search, prompt guardrails, and deployed it on AWS EC2, delivering reliable, production-grade responses that streamlined day-to-day InfoSec operations.

Data Analyst at SK Minerals and Additives Ltd (2025-07 – 2025-11)

• Engineered VendorSnap, a modular web scraping system automating vendor data extraction from IndiaMART, reducing the sales team's lookup time by over 90%.
• Developed a multi-variable regression model (8-10 process parameters) and used ANOVA to predict chemical production yields and identify key drivers of operational efficiency.

Data Analyst Intern at Excelerate (2025-04 – 2025-05)

• Led a 5-person analytics team as Project Head; designed SQL ETL pipelines for 100K+ records for an e-commerce data pipeline project, reducing exploratory analysis time by 40%.
• Awarded $1,000 Star Intern Scholarship by Saint Louis University for top performance and delivery excellence.

B.Tech in Computer Science (AI & ML) – Sandip University (2021 – 2025)