Navya Induri

Led enterprise-scale AI, Generative AI, and advanced analytics on Azure to support knowledge management, automation, decision support, and customer engagement. Architected RAG platforms using Azure OpenAI, LangChain/LlamaIndex, ChromaDB, and Azure AI Search, building robust multi-source retrieval pipelines across documents, APIs, and enterprise repositories. Engineered chunking/embedding/reranking and metadata enrichment strategies to improve retrieval quality and reduce hallucinations. Built agentic AI frameworks (LangGraph, CrewAI, AutoGen, Semantic Kernel) for multi-step reasoning and workflow orchestration, including multi-agent collaboration for planning, retrieval, validation, summarization, and recommendation generation. Implemented feedback-driven engineering and automated evaluation pipelines for relevance, groundedness, factual consistency, hallucination rate, latency, and retrieval effectiveness. Delivered responsible AI controls including prompt injection protection, PII ma

Designed and delivered enterprise AI solutions on AWS focused on predictive analytics, intelligent automation, recommendation systems, and cognitive AI to improve operational efficiency and decision-making. Collaborated with stakeholders and data engineering teams to define architectures and translate business needs into scalable ML/DL solutions. Developed classification models (Logistic Regression, SVM, Random Forest, Naïve Bayes, ensembles) for segmentation, risk assessment, and decision support; built clustering frameworks (K-Means, hierarchical clustering, DBSCAN) for hidden segments and anomaly detection; and created feature engineering pipelines (cleansing, encoding, normalization, dimensionality reduction, selection). Fine-tuned GPT-3 and adapted T5 on AWS to generate personalized content and reduce reliance on external models, lowering operational cost while maintaining quality. Built end-to-end ML pipelines on SageMaker with automated ingestion, preprocessing, training, valid

Built scalable backend and data processing systems using Python and big data tools. Developed reusable modules and automation frameworks to streamline operational processes and reduce manual effort. Implemented RESTful APIs and microservices for secure, scalable communication across internal and external systems. Created event-driven ingestion and processing pipelines using Apache Kafka/Flume and Spark for near real-time data delivery. Developed authentication/authorization mechanisms and secured API communications using token-based security and certificate handling. Orchestrated workflows on GCP to automate data movement and reporting, and exposed ML model predictions through APIs for enterprise applications. Implemented data preprocessing/validation frameworks to ensure high-quality datasets for analytics and ML. Built high-performance SQL components and containerized services with Docker and Kubernetes for consistent deployments. Supported CI/CD processes, automated testing, environ