Yashwanth Reddy Kantareddy

Designed and deployed LLM-powered AI applications using Python, AWS Bedrock, LangChain, and LangGraph to automate enterprise workflows and improve operational efficiency. Built production-grade RAG pipelines integrating vector databases and enterprise knowledge bases, improving response accuracy. Developed intelligent AI agents for multi-step reasoning and workflow orchestration, reducing manual effort. Integrated AI services with enterprise platforms using FastAPI and REST APIs. Optimized LLM/ML performance through prompt engineering, model evaluation, and inference optimization, reducing latency. Implemented MLOps pipelines with Docker, Kubernetes, AWS SageMaker, and CI/CD to accelerate deployment cycles and improve reliability.

Designed and deployed ML models using Python, TensorFlow, PyTorch, and scikit-learn to improve recommendation accuracy and customer engagement. Built scalable AI pipelines for preprocessing, feature engineering, model training, and inference, reducing deployment time. Developed predictive analytics with XGBoost and LightGBM to increase customer retention via personalized recommendations. Integrated models with enterprise applications using FastAPI and REST APIs for real-time insights. Optimized performance through hyperparameter tuning, feature selection, and continuous evaluation to improve accuracy and reduce inference latency. Implemented MLOps workflows using Docker, Kubernetes, MLflow, and CI/CD to improve production reliability.