Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Sai Yasheswini Kandimalla, an AI/ML Engineer with 4 years of experience designing, deploying, and operating production machine learning systems in healthcare and client-facing environments. I build end-to-end ML pipelines using Python, AWS SageMaker, MLflow, and FastAPI, transforming data into actionable insights and delivering measurable business impact such as 30% faster deployment cycles, large-scale data processing speedups, and improved predictive performance across risk modeling, NLP, and time-series forecasting. I own production monitoring, data drift checks, and retraining pipelines to ensure long-term model stability and regulatory compliance.…I am Sai Yasheswini Kandimalla, an AI/ML Engineer with 4 years of experience designing, deploying, and operating production machine learning systems in healthcare and client-facing environments. I build end-to-end ML pipelines using Python, AWS SageMaker, MLflow, and FastAPI, transforming data into actionable insights and delivering measurable business impact such as 30% faster deployment cycles, large-scale data processing speedups, and improved predictive performance across risk modeling, NLP, and time-series forecasting. I own production monitoring, data drift checks, and retraining pipelines to ensure long-term model stability and regulatory compliance.

Sai Yasheswini Kandimalla

Data Scientist, AI Engineer, AI Developer, +2





I am Sai Yasheswini Kandimalla, an AI/ML Engineer with 4 years of experience designing, deploying, and operating production machine learning systems in healthcare and client-facing environments. I build end-to-end ML pipelines using Python, AWS SageMaker, MLflow, and FastAPI, transforming data into actionable insights and delivering measurable business impact such as 30% faster deployment cycles, large-scale data processing speedups, and improved predictive performance across risk modeling, NLP, and time-series forecasting. I own production monitoring, data drift checks, and retraining pipelines to ensure long-term model stability and regulatory compliance.…I am Sai Yasheswini Kandimalla, an AI/ML Engineer with 4 years of experience designing, deploying, and operating production machine learning systems in healthcare and client-facing environments. I build end-to-end ML pipelines using Python, AWS SageMaker, MLflow, and FastAPI, transforming data into actionable insights and delivering measurable business impact such as 30% faster deployment cycles, large-scale data processing speedups, and improved predictive performance across risk modeling, NLP, and time-series forecasting. I own production monitoring, data drift checks, and retraining pipelines to ensure long-term model stability and regulatory compliance.

Available to hire

I am Sai Yasheswini Kandimalla, an AI/ML Engineer with 4 years of experience designing, deploying, and operating production machine learning systems in healthcare and client-facing environments.

I build end-to-end ML pipelines using Python, AWS SageMaker, MLflow, and FastAPI, transforming data into actionable insights and delivering measurable business impact such as 30% faster deployment cycles, large-scale data processing speedups, and improved predictive performance across risk modeling, NLP, and time-series forecasting. I own production monitoring, data drift checks, and retraining pipelines to ensure long-term model stability and regulatory compliance.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

AI/ML Engineer at Cigna

November 1, 2014 - Present

Designed, trained, and deployed supervised and ensemble ML models for healthcare risk and utilization prediction; built end-to-end production ML pipelines on AWS SageMaker with MLflow-based model versioning; reduced deployment turnaround time by 30%; performed large-scale EDA and statistical validation to improve robustness; developed time-series forecasting models (ARIMA, Prophet) to predict seasonal utilization; implemented NLP pipelines using Hugging Face Transformers and BERT for clinical and claims text classification and entity extraction; owned production monitoring and automated data drift checks and retraining pipelines to ensure long-term stability and regulatory compliance.

ML Engineer at Infinite Infolab

October 1, 2020 - July 1, 2023

Delivered production ML solutions across retail and operations domains; built distributed data processing pipelines using PySpark and Apache Spark; developed supervised and unsupervised models (Decision Trees, Random Forest, Gradient Boosting, K-Means) to improve segmentation, forecasting, and business decision-making; designed and analyzed A/B experiments; implemented MLOps workflows using MLflow and FastAPI for experiment tracking, model versioning, and API-based serving; collaborated cross-functionally with product managers and analysts to align ML solutions with real operational constraints.