Jahnavi Kolli

Built scalable data pipelines using Python and PySpark, processed large-scale datasets with optimized Spark transformations; deployed ML models for classification and predictive analytics using Scikit-learn and MLflow; designed end-to-end ML workflows including feature engineering, model training, evaluation, and deployment pipelines; integrated dashboards with Power BI to deliver real-time insights to stakeholders; applied MLOps practices including automated testing, monitoring, and CI/CD for reliable model deployment; collaborated with cross-functional teams to translate business and operational requirements into scalable ML solutions.

Developed ML models for demand forecasting and customer behavior analysis using Python and statistical techniques; optimized ETL pipelines using SQL and distributed data processing frameworks; built dashboards and reporting solutions to communicate insights to stakeholders; collaborated with cross-functional teams to translate insights into action and operational improvements.

Designed and implemented scalable ML systems using Python, PySpark and distributed data processing; built backend services and REST APIs using FastAPI to serve ML models in production environments; deployed microservices using Docker and AWS ECS/Fargate ensuring scalability and low-latency inference; integrated LLM APIs and Generative AI workflows for intelligent automation and decision systems; implemented CI/CD pipelines and MLOps workflows for model deployment, monitoring, and retraining; optimized data pipelines and inference systems reducing latency and improving performance.