Munvith Katpelly

5 years of professional experience in the Data Science field, specializing in statistical analysis, data mining, machine learning, and deep learning.
Led and delivered advanced data science initiatives while applying statistical analysis, data mining, machine learning, and deep learning techniques to solve complex business problems across multiple domains
Designed, developed, and optimized machine learning solutions using Python while automating data processing workflows and improving performance across model training and deployment pipelines
Built, containerized, and orchestrated production-grade ML workflows using Docker, Kubernetes, and Jenkins to enable reliable and scalable model deployment
Engineered, maintained, and optimized ETL pipelines using AWS Glue, Apache Spark, and Pandas to deliver high-quality, consistent datasets for analytics and reporting
Developed, secured, and integrated RESTful APIs in Python to operationalize analytics and machine learning models within production systems
Designed, built, and maintained interactive Power BI and Tableau dashboards while partnering with stakeholders to improve KPI visibility and data-driven decision-making
Applied statistical modeling and experimental design techniques while conducting hypothesis testing and A/B testing to validate insights and support product and operational decisions
Architected and managed cloud-based data and ML workflows across AWS and GCP while improving scalability, reliability, and cost efficiency of analytics platforms
Established version control standards and led collaborative development using Git, GitHub, and GitLab to support reliable releases and reproducible ML workflows
Implemented model tracking and experiment management workflows using MLflow while improving reproducibility and governance of machine learning experiments
Performed advanced data wrangling and transformation using SQL across MySQL and PostgreSQL while enabling reliable analytics and business reporting
Partnered with product, engineering, and QA teams and coordinated end-to-end delivery to ensure smooth promotion of data solutions from development into production
Designed, evaluated, and tuned a wide range of machine learning and deep learning models including ensemble methods, linear and logistic regression, support vector machines, gradient boosting, decision trees, clustering algorithms, probabilistic models, convolutional neural networks, and recurrent neural networks
Built, automated, and maintained data visualizations using Python and Power BI to communicate insights clearly and support executive and technical audiences
Led DevOps and MLOps practices by designing CI/CD pipelines and infrastructure as code using Docker, Kubernetes, and Terraform to streamline model deployment and lifecycle management
Architected and standardized data science workflows while improving reproducibility, testing, and deployment practices across multiple machine learning projects
Built and maintained scalable feature engineering pipelines and collaborated with platform teams to ensure consistency between training and production inference workflows
Designed and implemented data quality frameworks and partnered with upstream data producers to reduce data defects and schema drift
Designed and maintained orchestration workflows and improved pipeline reliability through scheduling, retries, backfills, and failure recovery strategies