Divya Reddy

About Divya Reddy

AI/ML Engineer with 4+ years of experience designing, developing, and deploying scalable machine learning and deep learning solutions across healthcare and enterprise domains. I specialize in building end-to-end ML pipelines—from data ingestion and feature engineering to model deployment and monitoring—using Python, TensorFlow, PyTorch, and scikit-learn. I have hands-on expertise in NLP, predictive analytics, and time series forecasting, with a strong focus on delivering production-ready solutions. My experience includes deploying models as REST APIs using FastAPI, implementing MLOps practices with MLflow and Airflow, and working across cloud platforms like AWS, GCP, and Azure. In my recent role, I developed healthcare risk prediction models and NLP solutions for clinical data, improving model accuracy by 25% while ensuring HIPAA compliance. I am passionate about leveraging data to solve real-world problems and continuously optimizing models for performance, scalability, and reliability. I thrive in collaborative Agile environments, working closely with data engineers, product teams, and stakeholders to deliver impactful AI-driven solutions.

Experience

1. Ai Ml Engineer

   Humana

   Jan 2025 — Present

   Designed and implemented end-to-end machine learning pipelines, including data ingestion, preprocessing, feature engineering, model training, validation, and deployment. Built predictive models using scikit-learn and TensorFlow to analyze patient data and improve healthcare outcomes. Developed NLP models to extract insights from unstructured clinical notes using SpaCy and transformer-based embeddings. Enhanced model accuracy by 25% through advanced feature engineering and hyperparameter tuning. Deployed models as scalable REST APIs using FastAPI and Docker across AWS and GCP environments. Established batch and real-time inference workflows using Airflow. Implemented MLflow for model tracking, versioning, and monitoring, including drift detection and automated retraining pipelines. Ensured data security and compliance with HIPAA standards. Automated CI/CD pipelines using GitHub Actions and Terraform, and collaborated cross-functionally to integrate ML solutions into enterprise systems.