Open to opportunities

Gaurav Saraswat

@gauravsaraswat

Message

Seasoned full-stack data professional delivering production-ready ML and data engineering solutions.

Germany

Message

What I'm looking for

I seek roles applying end-to-end data engineering and ML to production systems, emphasizing MLOps, scalable pipelines, and measurable business impact within collaborative, data-driven teams.

I am a seasoned data professional with nine years of experience at Bank of America and TCS and an MS in Data Science from TU Dortmund. I design and optimize end-to-end data pipelines, build production-ready machine learning models, and apply advanced techniques (SMOTE, XGBoost, PCA) to drive measurable business impact in fraud detection, risk mitigation, and large-scale analytics.

I have led ETL and data warehouse projects using IBM DataStage, Informatica MDM, Snowflake and cloud platforms (AWS, Azure, GCP), delivered automation that saved $500K annually, and contributed to enterprise-wide data quality and migration efforts. I combine engineering rigor with applied ML and MLOps (MLflow, Docker, CI/CD) to move models from prototype to production reliably.

Experience

Work history, roles, and key accomplishments

Senior Data & ML Engineer

Bank of America Continuum

Oct 2015 - May 2022 (6 years 7 months)

Architected and optimized end-to-end data pipelines and centralized DWHs to enable real-time ML and analytics; applied XGBoost with SMOTE to improve minority-class recall from 0.75 to 0.90 and raised PR AUC by 0.20 for fraud detection.

Python Pyspark XGBoost SMOTE Hadoop Data Warehousing MLFlow SQL Docker

Data Engineer

Tata Consultancy Services

Jan 2011 - Oct 2015 (4 years 9 months)

Built ETL workflows and global data warehouses (IBM DataStage, Informatica MDM) to support regulatory feeds and B2B reporting, reducing integration errors by 25% and improving data quality by 20%.

DataStage Informatica ETL Data Warehousing SQL Teradata