Balavardhan Sripuram

Designed and implemented enterprise-grade Generative AI systems using Retrieval-Augmented Generation (RAG) for intelligent knowledge retrieval and conversational AI. Built multi-agent AI workflows using LangChain, LangGraph, AutoGen, and Agentic AI frameworks, enabling autonomous task execution. Led AWS Bedrock-based Agentic AI platforms, including a multi-agent portfolio optimization MVP for financial intelligence use cases. Architected vector databases and scalable pipelines, and delivered Azure OpenAI-powered chatbots for internal automation. Implemented MLOps pipelines via MLflow, GitHub Actions, Azure DevOps, Kubernetes, and Databricks-based data pipelines; optimized cloud costs and governance.

Designed and implemented enterprise-grade Generative AI systems using Retrieval-Augmented Generation (RAG) for knowledge retrieval and conversational interfaces. Built multi-agent AI workflows with LangChain, LangGraph, AutoGen, and Agentic AI frameworks to orchestrate autonomous tasks. Developed AWS Bedrock-based Agentic AI platforms, including a multi-agent portfolio optimization MVP for financial intelligence use cases. Created and deployed LLM-based applications leveraging OpenAI GPT-5.x, Anthropic Claude, and Google Gemini 2.5 Pro. Architected vector databases (FAISS, Pinecone-like, Weaviate-style) for semantic search and enterprise knowledge retrieval. Designed scalable RAG pipelines with embedding strategies, prompt engineering, chunking optimization, and context retrieval tuning. Implemented MLOps pipelines (MLflow, GitHub Actions, Azure DevOps, Kubernetes) for CI/CD of GenAI models. Led cloud architecture design, cost optimization, governance, and ROI analysis for AI transform

Designed scalable AWS cloud architectures for enterprise aviation analytics; built big data pipelines with PySpark/SQL; delivered predictive analytics and ML models for forecasting and optimization; developed early-stage RAG prototypes for enterprise knowledge search and document intelligence; implemented real-time and batch data ingestion (S3, Lambda, EKS); containerized ML systems; improved Databricks workloads; supported migration to cloud-native microservices; built ARR/financial models; experimented with Agentic AI using AWS Bedrock.