Jigyashu Saravta

Data Scientist & Engineer with a strong foundation in building robust, cloud-native solutions and enabling data-driven decision-making at scale. Graduated with an MS in Information Management from UIUC and AWS Certified as a Data Engineer Associate, I bring a blend of backend engineering, real-time pipeline development, and applied analytics to solve high-impact business problems. 🚀 Highlights Designed and deployed real-time data streaming pipelines using Apache Kafka, Spark Structured Streaming, and AWS (S3, Glue, Athena), handling 150K+ messages and reducing batch latency to <7s Optimized Neo4j graph databases with 10M+ nodes, tuning memory, indexing, and APOC, achieving 75% faster query performance Delivered a full-stack Azure pipeline for Olympic data analytics – automated ETL (ADF), transformed via Spark, and visualized insights in Tableau Achieved 90%+ model accuracy for NLP classification of multilingual tweets (Hinglish–English) using LSTM; published in a Scopus-indexed journal Built ML models and analytics dashboards that monitor part failure trends, customer sentiment, and system health for real-world clients 🎯 What I Offer I thrive at the intersection of data engineering and applied data science — helping teams move from raw, messy data to automated systems and actionable insights. I enjoy solving messy pipeline problems just as much as analyzing churn, optimizing models, or scaling systems in the cloud. Let’s connect if you're building real-time intelligence, cloud-native platforms, or anything that turns data into value.