SRINATH BULUSU

I am a Data professional who bridges the gap between software engineering and advanced analytics. With a Master’s in Data Science and over 5 years of experience building scalable systems, I specialize in the full data lifecycle from modelling robust data pipelines using Snowflake ,Databricks along with cloud infrastructure to developing predictive machine learning models. Whether it is engineering clean data streams or uncovering deep business insights, I build production grade solutions that turn complex information into intelligent action.

1. Hands on experience designing, documenting and orchestrating robust data pipelines by collaborating with cross functional teams of 100+ users and supporting teams with data onboarding and quality checks using cloud platforms supporting batch and continous data workflows.

2. Deep expertise in Snowflake including SQL, Snowpark, Streams, Tasks, micro-partitioning, clustering, and performance tuning. Strong background in relational databases such as Snowflake, Oracle SQL, and SQL Server, with hands-on experience in data modeling and profiling.

3. Built a machine learning platform delivering real-time clinical risk alerts using ensemble models and Databricks pipelines. Also developed an AI-powered fitness tracker that provides personalized workout insights and predictive health recommendations.

4. Developed comprehensive risk assessment models using Deep Learning (CNN) and ensemble methods to evaluate loan repayment likelihood.Conducted extensive Quantitative Analysis on customer demographics and financial history, performing rigorous data cleaning to handle anomalies and missing values.

I am good at :

Data Engineering Tools: Snowflake, Databricks, Snowpark, AWS Glue, AWS Lambda, AWS S3, Alteryx
Database Tools: Oracle SQL, Microsoft SQL,SQL Server management Studio, SQL Workbench,NoSQL, MongoDB, Toad Data Point, Collibra, Palantir
Visualization Tools: Tableau, Informatica, Power BI, R
Programming Languages: SQL, Python, Javascript, C
ML Techniques: Linear Regression, Logistic Regression, Decision Trees, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, Gradient Boosting (XGBoost, AdaBoost), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Autoencoders, Deep Reinforcement Learning
Front End Tools: HTML, CSS, React JS, Typescript, Node JS
Other Tools: Git, GitHub, Flyway, Jira, Jenkins Pipeline, Microsoft Office (PowerPoint, Excel, Word)
Other Skills: Presentation skills, written and verbal communication skills, ability to work independently

My Work Experience

Company : Capgemini Technology Services
Period : May 2021 to Jan 2024
Client : Prudential Financial - Enterprise Data Architecture & Cloud Migration

Developed a scalable data ingestion framework for 100+ cross-functional teams, enabling structured onboarding of financial and healthcare data into Snowflake, ensuring 100% data quality compliance.
Engineered high-performance ETL/ELT pipelines using Snowpark (Python) and SQL to transform 15TB+ of raw data across six architectural layers, optimizing storage and retrieval speeds.
Designed serverless automation workflows using AWS Lambda and S3 triggers to ingest multi-format files (Parquet, JSON, XML), implementing auto-recovery mechanisms that reduced pipeline failure rates by 40%.
Implemented Change Data Capture (CDC) strategies to facilitate real-time analytics and maintain data integrity across distributed systems.
Established robust security governance by designing Role-Based Access Control (RBAC) policies and dynamic data masking, ensuring compliance with strict healthcare data privacy regulations.
Standardized deployment cycles by integrating GitHub,Jenkins for version control,Flyway for database version control within CI/CD pipelines, ensuring consistent environments across Dev, QA and Production.
Implemented Snowflake micro partitioning and clustering to optimize query performance, reduce scan costs, and improve large-scale analytics efficiency.Enabled secure Snowflake data sharing to other accounts supporting data access while maintaining governance and access controls.
Applied data classification techniques by tagging data elements based on a certain category and applying data masking for enhanced security. Enhanced data processing speed by implementing warehouse scaling and caching.

Client : Medica HealthCare - Data Warehouse Optimization

Optimized data warehousing capabilities by designing complex Snowflake ETL workflows, utilizing Streams and Tasks to automate SCD Type 1 & 2 historical data tracking.
Created complex snowflake views from raw source tables in snowflake using multi table joins, CTEs and mappings to standardize data.Worked on reducing query latency optimizing SQL queries by restructuring joins, reducing data scans, warehouse scaling ,caching , applying efficient filtering to improve query performance and execution time.
Automated job execution using Atomic scheduling tool,aligning technical workflows with workforce system operations.
Worked on flattening JSON data within raw tables to extract columns.Written transformation logic for multiple use cases and created member,med claim and pharmacy views from raw data.
Created resource monitors on warehouses for tracking credit consumption and optimize costs for the organization.

Company : Upen Group
Period : Aug 2019 to Apr 2021
Performance Analytics & Reporting

Improved reporting latency by 87% (reducing delay from 2 months to 1 week) by migrating manual reporting processes to automated cloud-based logic, enabling faster decision-making for leadership.
Developed and validated STMs with complex SQL transformation logic to build "Best Practice" scorecards, ranking providers on quality compliance and identifying gaps in care.
Designed emergency "At-Risk" data tables to centralize critical patient information, significantly improving response times for urgent care reporting for faster access to urgent care data, improved reporting accuracy for emergency cases.

My Projects

1. ProActiveCare: AI-Driven Patient Risk Prediction Platform

Designed and Engineered an end-to-end machine learning pipeline to predict ICU patient outcomes, achieving 99.7% accuracy and 95.1% recall by optimizing Random Forest and Gradient Boosting models.
Built a data ingestion framework on Databricks using Auto Loader and Delta Lake to clean and transform raw clinical data across medallion architecture (Bronze, Silver, Gold).
Addressed data imbalance significantly by applying SMOTE (Synthetic Minority Over-sampling Technique) and advanced feature imputation, enhancing the model's ability to detect high-risk cases.
Automated real-time risk alerts by integrating model outputs with external notification workflows, enabling proactive clinical intervention.

2. Personalized Fitness Tracker with AI-Based Insights

Developed a Full Stack web application incorporating AI-driven analytics to deliver personalized workout recommendations and real-time health tracking.
Integrated Natural Language Processing (NLP) to enable an intelligent conversational interface for effortless exercise logging and user interaction.
Designed a secure backend architecture with Node.js and Express.js, implementing JWT authentication to protect user health data.
Built dynamic dashboards in React to visualize user progress, using machine learning algorithms to adaptively adjust fitness goals based on historical activity data.

3. Home Credit Default Risk Prediction

Developed comprehensive risk assessment models using Deep Learning (CNN) and ensemble methods to evaluate loan repayment likelihood.
Conducted extensive Quantitative Analysis on customer demographics and financial history, performing rigorous data cleaning to handle anomalies and missing values.
Enhanced model performance through advanced Feature Engineering and hyperparameter tuning, successfully identifying key indicators of default risk to support financial decision making.

4. Traffic Accident Analysis & Prediction

Leveraged Long Short-Term Memory (LSTM) networks and Gradient Boosting to forecast traffic accident likelihood based on weather, road conditions and temporal factors.
Processed and cleaned 5 years of large scale accident data (FARS), ensuring high data integrity for statistical modeling.
Designed interactive Tableau dashboards to visualize accident hotspots and time-series patterns, providing actionable insights for road safety officials to allocate resources effectively.

Education

Masters Degree in Data Science at University of Texas at Arlington. GPA: 4.0 / 4.0
Bachelors Degree at Jawaharlal Nehru Technological University, India. CGPA: 8.03 / 10
12^th Standard Narayana Junior College. Percentage: 93.9%
10^th Standard Bhashyam High School. CGPA: 8.80/10

Certificates & Awards

Certifications:

SNOWPRO Associate by Snowflake (2026)
Python Essentials by Coursera (2021)
Snowflake Cloud Data Practitioner by Coursera (2021)
Associate Cloud Engineer from Google Cloud Platform (2021)

Awards & Recognition:

Rising Star in Q2 FY-23 for scaling up quickly to deliver high performance in the project.
Promotion as Senior Software Engineer at Capgemini within 1 year for delivering efficient solutions.