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

Hi, I'm Eswar Sai Korrapati, a results-driven software engineer with 3 years of experience specializing in building and deploying scalable machine learning models. I have a strong background in creating end-to-end ML pipelines, integrating large language models, and deploying explainable AI systems to help businesses make data-driven decisions. I'm passionate about optimizing model performance and automating workflows using MLOps tools like MLflow, SageMaker, and Apache Airflow. I enjoy collaborating in Agile environments and am always eager to learn new technologies that can enhance AI and ML applications.…Hi, I'm Eswar Sai Korrapati, a results-driven software engineer with 3 years of experience specializing in building and deploying scalable machine learning models. I have a strong background in creating end-to-end ML pipelines, integrating large language models, and deploying explainable AI systems to help businesses make data-driven decisions. I'm passionate about optimizing model performance and automating workflows using MLOps tools like MLflow, SageMaker, and Apache Airflow. I enjoy collaborating in Agile environments and am always eager to learn new technologies that can enhance AI and ML applications.

Eswar Sai Korrapati

AI Engineer, Data Scientist, Developer, +2





Hi, I'm Eswar Sai Korrapati, a results-driven software engineer with 3 years of experience specializing in building and deploying scalable machine learning models. I have a strong background in creating end-to-end ML pipelines, integrating large language models, and deploying explainable AI systems to help businesses make data-driven decisions. I'm passionate about optimizing model performance and automating workflows using MLOps tools like MLflow, SageMaker, and Apache Airflow. I enjoy collaborating in Agile environments and am always eager to learn new technologies that can enhance AI and ML applications.…Hi, I'm Eswar Sai Korrapati, a results-driven software engineer with 3 years of experience specializing in building and deploying scalable machine learning models. I have a strong background in creating end-to-end ML pipelines, integrating large language models, and deploying explainable AI systems to help businesses make data-driven decisions. I'm passionate about optimizing model performance and automating workflows using MLOps tools like MLflow, SageMaker, and Apache Airflow. I enjoy collaborating in Agile environments and am always eager to learn new technologies that can enhance AI and ML applications.

Available to hire

Hi, I’m Eswar Sai Korrapati, a results-driven software engineer with 3 years of experience specializing in building and deploying scalable machine learning models. I have a strong background in creating end-to-end ML pipelines, integrating large language models, and deploying explainable AI systems to help businesses make data-driven decisions.

I’m passionate about optimizing model performance and automating workflows using MLOps tools like MLflow, SageMaker, and Apache Airflow. I enjoy collaborating in Agile environments and am always eager to learn new technologies that can enhance AI and ML applications.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Software Engineer – AI/ML at Comcast

August 1, 2024 - Present

Designed and deployed production-grade ML models using TensorFlow and PyTorch, improving prediction accuracy by 20% in real-time streaming systems. Built reproducible ML workflows using Apache Airflow, MLflow, and DVC, enabling versioned pipelines and consistent experiment tracking. Deployed models using AWS SageMaker and Lambda, cutting infrastructure costs by 15% and reducing deployment time by 35%. Applied SHAP and LIME to create explainability dashboards for stakeholder decision-making and regulatory compliance. Automated hyperparameter tuning with SageMaker Autopilot and Optuna, leading to an 18% improvement in model F1 score. Built scalable batch inference pipelines with Apache Spark and AWS S3, reducing inference time by 25%. Integrated LLM-based chat capabilities using OpenAI API and prompt engineering to enhance customer support automation. Collaborated within Agile teams using Git, Docker, and Jenkins to streamline CI/CD across ML lifecycles.

Software Engineer at Dentsu

July 31, 2022 - July 24, 2025

Engineered RESTful APIs and backend logic using Django and Flask, increasing system throughput and API response efficiency. Developed automated ML workflows using Apache Airflow, improving pipeline reliability and scheduling. Containerized and deployed web services via Docker and AWS EC2 for high availability and faster deployments. Built a centralized Feature Store standardizing feature reuse across models, speeding experimentation. Leveraged AutoML tools for ad campaign forecasting, reducing manual tuning by 40% and improving accuracy. Integrated model evaluation metrics and Tableau for enhanced stakeholder reporting. Managed AWS cloud resources, automated deployments with Jenkins, and versioned projects using Git and GitHub Actions.

Software Engineer – AI/ML at Comcast

August 1, 2024 - Present

Designed and deployed production-grade ML models using TensorFlow and PyTorch, improving prediction accuracy by 20% in real-time streaming systems. Built reproducible ML workflows using Apache Airflow, MLflow, and DVC, enabling versioned pipelines and consistent experiment tracking. Deployed models using AWS SageMaker and Lambda, cutting infrastructure costs by 15% and reducing deployment time by 35%. Applied SHAP and LIME to create explainability dashboards, aiding stakeholders in data-driven decision-making and regulatory compliance. Automated hyperparameter tuning using SageMaker Autopilot and Optuna, leading to an 18% improvement in model F1 score. Built scalable batch inference pipelines with Apache Spark and AWS S3, reducing inference time by 25% across large datasets. Integrated LLM-based chat capabilities using OpenAI API and prompt engineering, enhancing customer support response automation. Collaborated in Agile teams using Git, Docker, and Jenkins to streamline CI/CD across

Software Engineer at Dentsu

July 31, 2022 - July 24, 2025

Engineered RESTful APIs and backend logic using Django and Flask, increasing system throughput and API response efficiency. Developed automated ML workflows using Apache Airflow, improving pipeline reliability and scheduling across data ingestion tasks. Containerized and deployed web services via Docker and AWS EC2, achieving high availability and faster deployment cycles. Built a centralized Feature Store to standardize feature reuse across models, improving experimentation speed and consistency. Leveraged AutoML tools for ad campaign forecasting, reducing manual tuning time by 40% and improving prediction accuracy. Integrated model evaluation metrics and visualization tools like Tableau to enhance stakeholder reporting. Managed cloud resources using AWS, automated deployments with Jenkins, and versioned projects via Git and GitHub Actions.

Software Engineer – AI/ML at Comcast

August 1, 2024 - Present

Designed and deployed production-grade ML models using TensorFlow and PyTorch, improving prediction accuracy by 20% in real-time streaming systems. Built reproducible ML workflows using Apache Airflow, MLflow, and DVC, enabling versioned pipelines and consistent experiment tracking. Deployed models using AWS SageMaker and Lambda, cutting infrastructure costs by 15% and reducing deployment time by 35%. Applied SHAP and LIME to create explainability dashboards for stakeholders. Automated hyperparameter tuning leading to an 18% improvement in model F1 score. Built scalable batch inference pipelines with Apache Spark and AWS S3, reducing inference time by 25%. Integrated LLM-based chat capabilities via OpenAI API, enhancing customer support automation. Collaborated in Agile teams using Git, Docker, and Jenkins to streamline CI/CD across ML lifecycles.

Software Engineer at Dentsu

July 31, 2022 - July 24, 2025

Engineered RESTful APIs and backend logic using Django and Flask to increase system throughput and API response efficiency. Developed automated ML workflows with Apache Airflow, improving pipeline reliability and scheduling. Containerized and deployed web services with Docker and AWS EC2 for high availability and faster deployment. Built a centralized Feature Store to standardize feature reuse across models, improving experimentation speed and consistency. Leveraged AutoML tools for ad campaign forecasting, reducing manual tuning by 40% and improving accuracy. Integrated evaluation metrics and visualization tools like Tableau for stakeholder reporting. Managed cloud resources with AWS, automated deployments using Jenkins, and versioned projects with Git and GitHub Actions.