vishveshwara guthal

I am a data engineer with strong expertise designing real-time and batch data pipelines using Apache Spark, Kafka, Hive, and cloud platforms. I have delivered measurable performance improvements — including 30% processing gains, 40% faster throughput, and 5x faster query execution — while building monitoring and automated reporting to ensure data quality.

My background spans production engineering, geospatial analytics, and applied machine learning; projects include an NY real-estate valuation platform (89% forecast accuracy) and OCR-based form digitization for regional administrative data. I develop end-to-end solutions incorporating Python, R, Spark, and visualization tools such as Tableau and Plotly.

I seek to bring pragmatic, metrics-driven engineering to teams focused on scalable data systems, real-time analytics, and operationalizing ML — leveraging cloud services (GCP/AWS), streaming, and geospatial processing to drive business outcomes.