Nikhila B
Hartford,CT
Summary
Accomplished MLOps Engineer with a proven track record at CIGNA, enhancing model efficiency and reducing costs by 20% through expert deployment of AWS, Docker, and Kubernetes. Skilled in Python and collaborative project management, I excel in automating and optimizing ML pipelines, ensuring scalable solutions and actionable insights in healthcare analytics.
Overview
9
9
years of professional experience
Work History
MLOps Engineer
CIGNA
Bloomfield, CT
06.2023 - Current
- Designed and implemented end-to-end machine learning pipelines on AWS SageMaker, achieving a 30% reduction in model training time
- Automated data preprocessing using AWS Glue and Lambda, handling over 1TB of healthcare claims data daily
- Built and deployed containerized ML models using Docker and Kubernetes, ensuring scalable and reliable infrastructure
- Developed CI/CD pipelines for ML models using Jenkins and Terraform, reducing deployment cycles by 40%
- Conducted model testing and evaluation using Python libraries like Scikit-learn and TensorFlow, improving model accuracy by 15%
- Designed dimensional data models for healthcare analytics using Snowflake, enabling faster reporting and insights
- Integrated AWS RDS and DynamoDB for structured and semi-structured data storage, ensuring high availability and fault tolerance
- Created Redshift clusters optimized for complex queries, reducing report generation times by 50%
- Implemented AWS CloudFormation templates for automated infrastructure provisioning, ensuring consistency across environments
- Monitored model performance with Prometheus and Grafana, identifying issues and minimizing downtime
- Designed and maintained data lakes on AWS S3 for large-scale data processing and analytics
- Conducted A/B testing for healthcare policy recommendation models, optimizing patient outcomes
- Created interactive dashboards in Power BI for visualizing model predictions and healthcare trends
- Enhanced ETL processes using PySpark, reducing data processing time by 25%
- Partnered with data scientists to optimize feature engineering workflows, improving model performance
- Migrated on-premise ML workflows to AWS, achieving a 20% reduction in infrastructure costs
- Defined and implemented data governance policies to ensure compliance with HIPAA regulations
- Built real-time anomaly detection systems using SageMaker and Lambda, enhancing fraud detection capabilities
- Implemented Snowflake pipelines for integrating data from various sources, ensuring data consistency
- Deployed NLP models for analyzing patient feedback, improving customer satisfaction by 10%
- Developed monitoring scripts for database performance, identifying bottlenecks and optimizing queries
- Automated the generation of healthcare KPIs using Python and SQL, reducing manual effort by 60%
- Conducted root cause analysis for pipeline failures, improving system reliability by 95%
- Integrated Kafka for real-time data streaming, supporting dynamic model updates
- Optimized SageMaker endpoints for low-latency predictions, reducing response times by 30%
- Conducted workshops for teams on AWS services and MLOps best practices, improving collaboration
- Collaborated with stakeholders to define project requirements and deliver actionable insights
- Designed and deployed scalable dimensional models, enabling advanced analytics and decision-making
- Ensured robust security measures for ML pipelines, including encryption and access controls
Machine Learning Engineer
ClearResults ATLAS
Austin, TX
04.2018 - 12.2022
- Built and deployed scalable ML pipelines using AWS SageMaker, enhancing operational efficiency by 35%
- Automated data transformation workflows using AWS Glue, handling over 500GB of energy consumption data daily
- Designed ETL processes with PySpark and Snowflake, reducing data transformation time by 40%
- Created CI/CD pipelines for model deployment using Jenkins and Docker, ensuring robust version control
- Developed and maintained data warehouses using Redshift and DynamoDB, supporting large-scale analytics
- Designed dimensional data models for energy usage analytics, enabling faster reporting
- Integrated Tableau and Power BI for creating dashboards to visualize energy-saving trends and forecasts
- Conducted model testing and validation using Python, ensuring deployment of high-accuracy models
- Monitored ML pipeline performance with Prometheus, identifying and resolving bottlenecks
- Built real-time prediction systems for energy demand forecasting, improving accuracy by 20%
- Automated infrastructure provisioning using Terraform and AWS CloudFormation, ensuring reliability
- Enhanced system monitoring and logging using CloudWatch, improving incident response times
- Migrated legacy systems to AWS, achieving a 25% reduction in operational costs
- Partnered with stakeholders to implement machine learning solutions aligned with business goals
- Conducted A/B testing to optimize model predictions, improving energy savings by 15%
- Utilized Apache Kafka for real-time data ingestion, supporting dynamic ML workflows
- Designed secure pipelines for sensitive energy data, ensuring compliance with industry standards
- Developed training modules for teams on MLOps tools and best practices, fostering skill development
- Created interactive dashboards to track ML model performance and business KPIs
- Conducted root cause analysis for pipeline failures, achieving a 98% uptime for critical workflows
- Integrated Snowflake pipelines for seamless data transformation and analytics
- Improved database query performance by indexing and optimizing Redshift configurations
- Automated the creation of energy consumption reports using Python, reducing manual effort by 50%
- Deployed NLP models for customer feedback analysis, enhancing service quality
- Built APIs for integrating ML predictions into business applications, enabling real-time decision-making
- Conducted code reviews to ensure adherence to MLOps best practices
- Enhanced AWS S3 storage configurations to support cost-efficient data archiving
MLOps/Data Engineer
Tricon Infotech pvt.ltd
Bangalore, India
11.2015 - 03.2018
- Designed and implemented ETL pipelines using PySpark, Snowflake, and AWS Glue, processing over 1TB of logistics data daily
- Built dimensional data models to support supply chain analytics, improving reporting efficiency by 40%
- Created AWS S3 data lakes for centralized data storage and analytics
- Automated model deployment workflows using Docker and Kubernetes, reducing deployment times by 30%
- Developed CI/CD pipelines with Jenkins, ensuring consistent and error-free deployments
- Optimized database performance for Oracle and MySQL, achieving faster query execution
- Conducted model validation and testing using Python, ensuring reliable predictions
- Created dashboards in Power BI and Tableau to monitor logistics KPIs and trends
- Enhanced system reliability by implementing data validation scripts and monitoring tools
- Collaborated with teams to define data governance policies, ensuring data quality and compliance
- Migrated on-premise systems to AWS, achieving a 20% reduction in costs
- Implemented streaming solutions with Kafka for real-time logistics tracking
- Conducted A/B testing to optimize supply chain models, improving efficiency by 15%
- Built and maintained secure pipelines for sensitive data, ensuring regulatory compliance
- Designed and deployed real-time anomaly detection systems, reducing operational disruptions
- Automated daily reporting tasks using Python and SQL, saving 10+ hours weekly
- Enhanced operational dashboards to provide actionable insights for decision-makers
- Conducted workshops for teams on ETL and MLOps tools, fostering knowledge sharing
- Partnered with stakeholders to implement machine learning solutions tailored to business needs
- Developed and deployed APIs for integrating predictive models into business applications
- Improved the efficiency of logistics operations by implementing data-driven optimization models
Education
Master of Science - Data Science
University of Connecticut
Hartford, CT05-2024
Bachelor - Computer Science And Engineering
Jawaharlal Nehru Technological University
India 04-2016
Skills
- Python
- SQL
- R
- Java
- Shell Scripting
- MATLAB
- NoSQL
- Docker
- Kubernetes
- Jenkins
- Terraform
- PySpark
- MLflow
- Airflow
- Kafka
- Model Deployment
- Hyperparameter Tuning
- A/B Testing
- Feature Engineering
- AWS
- GCP
- Azure
- MySQL
- PostgreSQL
- MongoDB
- Redshift
- Snowflake
- SparkSQL
- Power BI
- Tableau
- Seaborn
- Matplotlib
Timeline
MLOps Engineer
CIGNA
06.2023 - Current
Machine Learning Engineer
ClearResults ATLAS
04.2018 - 12.2022
MLOps/Data Engineer
Tricon Infotech pvt.ltd
11.2015 - 03.2018
Master of Science - Data Science
University of Connecticut
Bachelor - Computer Science And Engineering
Jawaharlal Nehru Technological University
Similar Profiles
Rudee FriarRudee Friar
Customer Service Representative at CignaCustomer Service Representative at Cigna
Luis GilLuis Gil
Customer Service Representative at CignaCustomer Service Representative at Cigna
TIA WHITETIA WHITE
Senior Enrollment / Medical Billing Specialist at CignaSenior Enrollment / Medical Billing Specialist at Cigna
Zorielle RobertsonZorielle Robertson
Customer Service Representative at CignaCustomer Service Representative at Cigna
Omar MattesonOmar Matteson
Painter, Home Improvement at Omar Painting and Home Improvement Perfections LlcPainter, Home Improvement at Omar Painting and Home Improvement Perfections Llc