Data Engineer Financial Services

Sai Chandra Vanama

573-***-**** *****************@*****.*** LinkedIn GitHub

SUMMARY

Data Science Engineer with 4 years of experience in data engineering, applied machine learning, and cloud-native analytics across SaaS, financial services, and enterprise IT. Skilled in building ETL/ELT pipelines (Airflow, dbt, AWS, Snowflake), deploying real-time dashboards (Power BI, Tableau), and developing predictive models (churn, fraud, forecasting). Adept at leveraging Generative AI, NLP, and statistical modeling to deliver actionable insights, optimize workflows, and drive business outcomes.

SKILLS

Programming & Data: Python (Pandas, NumPy, scikit-learn), R, SQL

Data Engineering & ETL: Airflow, dbt, ETL/ELT automation, Data Cleaning

Databases & Cloud: Snowflake, AWS (S3, Redshift, Lambda), PostgreSQL, MySQL

ML: Classification/Regression, Churn/Fraud Prediction, Feature Engineering, Model Monitoring & Drift Detection

GenAI & NLP: Prompt Engineering, LLM Integration, Sentiment Analysis, TF-IDF

Visualization & Reporting: Tableau, Power BI, KPI Dashboards, Automated Reporting

EXPERIENCE

VMware Data Science Engineer

Domain: Cloud / SaaS (Customer Analytics & Predictive Modeling) Jan 2025 – Present

Improved predictive model accuracy by performing data wrangling, EDA, and statistical profiling on large-scale datasets using SQL and Python, which provided more reliable insights for churn and usage forecasting.

Designed and deployed interactive Tableau dashboards to track feature adaptation, usage patterns, and customer engagement, enabling product teams to make faster and better data-driven decisions.

Optimized Snowflake SQL queries for recurring analytics workflows, cutting dashboard refresh times by 40% and reducing cloud costs, which improved efficiency for business reporting.

Collaborated with ML engineers to enhance churn prediction and usage forecasting models, ensuring accurate and timely ingestion of multi-source data from AWS-hosted ETL pipelines.

Implemented KPI tracking and hypothesis testing frameworks to measure the impact of product features across customer segments, supporting leadership in evaluating new initiatives.

Integrated datasets from product, finance, and marketing domains to deliver accurate and compliant insights that aligned with organizational reporting needs.

MoneyGram Data Science Intern

Domain : Financial Services Apr. 2024 – Aug 2024

Automated Python workflows to generate ML training datasets, reducing manual preparation time by 30% and enabling faster experimentation cycles for compliance projects.

Conducted EDA on 1M+ transaction records to detect anomalies and usage patterns, supporting fraud detection and regulatory reporting initiatives with higher accuracy.

Partnered with engineers to integrate AWS Redshift pipelines into ML workflows, cutting data prep latency by 40% and improving the scalability of analytics reporting.

Built interactive dashboards in Tableau and Power BI to visualize transaction trends, reducing stakeholder decision-making time by 15% and enhancing visibility.

Combined multi-source datasets from finance, product, and marketing domains to deliver compliance-driven insights that improved reporting consistency across teams.

Dell Technologies Software Analyst

Domain: Enterprise IT Apr 2021 – Aug 2023

Delivered KPI dashboards and insights using SQL, Python, and Power BI, enabling leadership to monitor performance and optimize operations across multiple regions.

Supported predictive analytics for retention and demand forecasting by developing models in Python (scikit-learn), improving forecast accuracy and decision-making.

Automated ETL workflows with Apache Airflow, improving data pipeline reliability, reducing manual interventions, and ensuring timely delivery of critical business reports.

Optimized PostgreSQL and MySQL queries by tuning indexes and analyzing execution plans, which reduced report runtimes by 2–5 and improved system performance.

Designed and deployed interactive dashboards for cross-functional teams, streamlining weekly reporting cycles and enhancing decision-making efficiency.

EDUCATION

Masters’s in Computer Science May 2025

Southeast Missouri State University, USA

PROJECT

Flappy Bird AI GitHub Link

Tools: Python, Flask, Pygame, NumPy, Neural Networks, Genetic Algorithm

Developed an AI agent to play the Flappy Bird game by combining neural networks with a custom genetic algorithm. Implemented core game mechanics such as gravity, pipes, and collision detection in Pygame, while training agents through fitness-based evaluation. Built a Flask web interface to visualize the AI’s learning process in real time, and optimized hyperparameters to improve convergence and overall performance. This project gave me hands-on experience in connecting AI concepts with game development in a practical way.

Contact this candidate