Ruthvik K Email & Phone Number

Gainesville, Florida, United States

Developed and deployed machine learning models for customer churn prediction, fraud detection, and risk assessment, improving business outcomes and reducing churn rates.Implemented forecasting models like ARIMA and Holt-Winter for business insights, optimizing resource allocation and improving decision-making.Designed and deployed scalable ETL pipelines using AWS services (EC2, S3, RDS) and tools like Apache Beam and Snowflake, significantly enhancing data retrieval efficiency.Optimized pricing models using Bayesian optimization and hyperparameter tuning, improving model precision and reducing loss ratios by 10%.Implemented real-time fraud detection models using machine learning algorithms, enhancing security and preventing fraud in online transactions.Leveraged Large Language Models (LLMs) like GPT-4 and Ollama to build intelligent customer support chatbots, improving customer satisfaction by 20% and reducing response times by 35%.Automated claims processing using NLP models (BERT, GPT), reducing manual effort by 40% and improving processing time by 30%.Developed and managed CI/CD pipelines (Jenkins, AWS CodePipeline) for seamless model deployment, ensuring robust performance and efficient scaling.Built Docker containers for managing application lifecycles, improving scalability and deployment efficiency across cloud platforms.Led credit analysis and risk modeling algorithms to optimize customer acquisition strategies, delivering actionable insights and enhancing business decisions.

Pittsburgh, Pennsylvania, United States

Developed and deployed machine learning models for predicting customer churn, fraud detection, and credit risk, which significantly improved business decision-making and customer retention strategies.Built data pipelines and warehouses using AWS, Azure, and GCP cloud platforms, including services like Apache Airflow and Azure Data Factory, which streamlined data flow and improved processing efficiency by 50%.Implemented NLP and transformers (BERT, GPT) to automate claims processing and customer interactions, improving service response times by 35% and reducing manual effort by 40%.Engineered forecasting models like ARIMA, Holt-Winter, and survival analysis to optimize resource allocation, improve customer acquisition, and reduce operational costs.Leveraged LLMs (GPT-4, Ollama) and GANs to build generative models for synthetic data and customer support chatbots, reducing reliance on sensitive data and improving customer satisfaction by 20%.Integrated real-time fraud detection models into banking and insurance platforms, enhancing fraud prevention across transactions and lowering risk exposure.Designed and deployed ETL pipelines for large datasets across healthcare and financial sectors, reducing data processing times and increasing accessibility for analytics and reporting.Optimized pricing models using Bayesian optimization and hyperparameter tuning, improving model precision and reducing loss ratios by 10% in insurance models.Deployed containerized applications using Docker and Kubernetes for scalable infrastructure across healthcare data processing applications, ensuring high availability and compliance with regulatory standards (HIPAA, GDPR).Designed and implemented CI/CD pipelines (Jenkins, Azure DevOps) for continuous integration and deployment of data and ML models, reducing deployment failures and improving overall development efficiency.

Florida, United States

• Designed and implemented data warehousing solutions using GCP BigQuery and Cloud Spanner to support large-scale data analysis and decision-making processes.• Developed and maintained robust data pipelines using Cloud Dataflow and Apache Beam, ensuring efficient data processing and transformation.• Managed and optimized data storage solutions using GcsBucket and Cloud Storage Transfer Service to ensure data availability and disaster recovery.• Automated data workflows using Cloud Composer and G-Cloud Function to streamline data management tasks and reduce manual intervention.• Integrated Snowflake with GCP services to enhance analytics and reporting capabilities, providing deeper insights into insurance claims and customer interactions.• Utilized Cloud Pub/Sub for real-time data messaging and event-driven processing, improving response times and system interactivity.• Configured and operated Cloud SQL and VM Instances to support various database management systems, including MySQL, Postgres, and SQL Server.• Employed Data Catalog to create a metadata repository that enhances data discoverability and governance across the organization.• Scripted complex data extraction, transformation, and loading tasks using Gsutil and Bq Command Line Utilities.• Orchestrated data integration and synchronization across distributed systems using Sqoop and Cloud Spanner to maintain data consistency and reliability.• Developed scalable applications using Python and Scala within the GCP Databricks and Dataproc environments to process and analyze large datasets.• Implemented Spark and Spark-SQL for complex data processing tasks, enhancing data manipulation and retrieval capabilities.• Utilized Hive for managing large datasets residing in distributed storage and queried using SQL syntax.• Created dashboards and reports using data from Salesforce SOQL to provide actionable insights into customer behavior and claims management.

New York, United States

Developed and maintained robust data pipelines using Cloud Dataflow and Apache Beam, optimizing fraud detection systems and streamlining financial reporting.Utilized Cloud Pub/Sub for real-time messaging and event-driven processing, improving responsiveness in high-frequency trading and financial fraud detection.Integrated Snowflake with GCP services, enhancing reporting for customer insights, loan risk analysis, and investment portfolio management.Implemented Spark and Spark-SQL to manage complex financial data processing, improving data manipulation speed for large-scale banking operations like mortgage lending.Configured and managed Cloud SQL and VM Instances, ensuring secure and efficient data storage for customer transaction records and supporting core banking applications.Automated ETL workflows using Cloud Composer and G-Cloud Functions, reducing manual intervention and enabling real-time updates for customer and account data.Developed scalable credit scoring applications using Python and Scala within GCP Dataproc and Databricks, enhancing financial risk assessments for loans.Orchestrated data integration across banking systems with Sqoop and Cloud Spanner, ensuring consistency and reliability of transactional data across multiple banking regions.Created interactive dashboards using Salesforce SOQL, providing actionable insights for business decision-making related to loan performance and customer engagement.Monitored and audited GCP environments, ensuring optimal performance for mission-critical banking applications and compliance with industry security standards (e.g., PCI-DSS).

Hyderabad, Telangana, India

• Led the development of large-scale data processing systems using Hadoop ecosystem technologies like MapReduce, Hive, and Pig; focused on constructing complex data pipelines and interactive dashboards, enhancing business decision-making and operational efficiency.• Implemented data ingestion and transformation solutions with Sqoop and Informatica, enabling seamless data flow from Oracle databases to Hadoop environments, which optimized data accessibility and analysis capabilities.• Enhanced data warehouse operations by integrating MicroStrategy with Hive, improving report generation speed and accuracy which resulted in a 40% increase in user satisfaction for data-driven insights.• Managed Hadoop clusters using Cloudera Manager, ensuring high availability and performance tuning that supported critical business applications and data processing tasks.• Automated workflow management by developing and maintaining Oozie jobs, which streamlined processing schedules and reduced manual oversight by 30%.• Optimized data storage and retrieval processes by configuring and maintaining Zookeeper, improving system stability and response times for high-volume data operations.• Conducted batch processing tasks through effective MapReduce programs, significantly reducing processing time by automating data aggregation and summarization processes.• Deployed robust data security and governance frameworks within the Hadoop ecosystem, ensuring compliance with enterprise and regulatory standards, thus safeguarding sensitive information.• provided technical guidance and leadership in the migration of legacy systems to Hadoop platforms, overseeing the strategic use of tools like Hive, Pig, and Sqoop to ensure a smooth transition and minimal downtime.