Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a Data Engineer and Applied Data Scientist with 4+ years of building reliable data pipelines and production-ready ML systems. I am proficient in PySpark, Airflow, Databricks, AWS, Snowflake, XGBoost, and TensorFlow, and I design automated training workflows and model monitoring to deliver measurable business value. In my roles at Capital One and DXC Technology, I have cut processing times from hours to minutes, boosted fraud signal precision, reduced cloud spend, and accelerated ML deployment cycles. I also implemented streaming checks with Kinesis and built Power BI dashboards to surface drift and risk patterns for faster leadership decisions.…I am a Data Engineer and Applied Data Scientist with 4+ years of building reliable data pipelines and production-ready ML systems. I am proficient in PySpark, Airflow, Databricks, AWS, Snowflake, XGBoost, and TensorFlow, and I design automated training workflows and model monitoring to deliver measurable business value. In my roles at Capital One and DXC Technology, I have cut processing times from hours to minutes, boosted fraud signal precision, reduced cloud spend, and accelerated ML deployment cycles. I also implemented streaming checks with Kinesis and built Power BI dashboards to surface drift and risk patterns for faster leadership decisions.

Prudhvi Sai K

Data Scientist, Data Analyst, AI Engineer, +2





I am a Data Engineer and Applied Data Scientist with 4+ years of building reliable data pipelines and production-ready ML systems. I am proficient in PySpark, Airflow, Databricks, AWS, Snowflake, XGBoost, and TensorFlow, and I design automated training workflows and model monitoring to deliver measurable business value. In my roles at Capital One and DXC Technology, I have cut processing times from hours to minutes, boosted fraud signal precision, reduced cloud spend, and accelerated ML deployment cycles. I also implemented streaming checks with Kinesis and built Power BI dashboards to surface drift and risk patterns for faster leadership decisions.…I am a Data Engineer and Applied Data Scientist with 4+ years of building reliable data pipelines and production-ready ML systems. I am proficient in PySpark, Airflow, Databricks, AWS, Snowflake, XGBoost, and TensorFlow, and I design automated training workflows and model monitoring to deliver measurable business value. In my roles at Capital One and DXC Technology, I have cut processing times from hours to minutes, boosted fraud signal precision, reduced cloud spend, and accelerated ML deployment cycles. I also implemented streaming checks with Kinesis and built Power BI dashboards to surface drift and risk patterns for faster leadership decisions.

Available to hire

I am a Data Engineer and Applied Data Scientist with 4+ years of building reliable data pipelines and production-ready ML systems. I am proficient in PySpark, Airflow, Databricks, AWS, Snowflake, XGBoost, and TensorFlow, and I design automated training workflows and model monitoring to deliver measurable business value.

In my roles at Capital One and DXC Technology, I have cut processing times from hours to minutes, boosted fraud signal precision, reduced cloud spend, and accelerated ML deployment cycles. I also implemented streaming checks with Kinesis and built Power BI dashboards to surface drift and risk patterns for faster leadership decisions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Advanced

Work Experience

Data Engineer | Data Scientist at Capital One Financial

August 1, 2024 - Present

Rebuilt high-volume credit pipelines in PySpark and Airflow, reducing data processing time from hours to minutes and improving reliability for daily financial data access. Improved fraud-signal precision by 23% by refining features, segmenting transaction patterns, and retraining models in SageMaker using XGBoost and TensorFlow, reducing false alerts across card portfolios. Trimmed Snowflake and Redshift spend by 38% via schema redesign, partition tuning, and incremental loading, and reduced query latency for risk analysts. Automated ML deployment checks, versioning, and rollback with MLflow and GitHub Actions, cutting deployment cycles from eight days to two. Introduced streaming checks using Kinesis to monitor live payment activity for faster fraud response. Built Power BI dashboards surfacing model drift, alert volumes, and risk patterns to support executive decision-making.

Data Engineer | Data Analyst at DXC Technology

February 1, 2021 - December 1, 2022

Improved nightly data pipeline runtime by 30% through Spark optimization, caching, and stable Delta Lake design, ensuring timely reports and downstream updates. Delivered a 22% lift in forecasting accuracy for staffing and asset planning via targeted feature engineering and clean modeling pipelines in Python and Scikit-learn. Increased analytics usage by leadership by 60% with reliable dashboards in Power BI and Tableau and automated refreshes. Reduced manual data cleanups by introducing data checks, anomaly alerts, and SLA monitoring within ADF and Databricks flows. Strengthened governance through RBAC and encryption across reporting layers.

Data Analyst – IoT & Project Analytics at Larsen & Toubro (L&T Construction)

February 1, 2020 - January 1, 2021

Lowered equipment downtime by 18% by analyzing sensor feeds in Spark and flagging early failure patterns. Transitioned reporting from manual spreadsheets to automated Python + SQL + Power BI workflows, delivering same-day insights for project managers. Improved material and schedule forecasting with time-series techniques and monitoring variance across active project sites. Increased trust in reporting by adding validation rules and source tracking, reducing disputes.