Anupa Bhattacharyya
Senior Technical Account Manager, AWS
Philadelphia, New York, United States
Actions
Anupa Bhattacharyya is a Senior Technical Account Manager at Amazon Web Services, where she guides enterprise customers through their cloud journey. With over 15 years of experience in data and analytics, she excels in defining strategic initiatives for enterprise customers. Outside of work, she enjoys painting, traveling, family time, and savoring new cuisines.
Links
Area of Expertise
Topics
AI-Powered OpenSearch Management using Kiro CLI and the OpenSearch MCP Server
Managing Amazon OpenSearch Service clusters demands deep domain expertise from index lifecycle management and shard rebalancing to fine-grained access control and vector search tuning for generative AI workloads. These tasks require repetitive REST API calls, hand-crafted JSON configurations, and constant context-switching across documentation. What if you could manage your OpenSearch cluster the same way you'd describe a task to a colleague in plain English?
This session demonstrates how agentic AI transforms OpenSearch operations. Using Kiro CLI with the open-source OpenSearch MCP (Model Context Protocol) Server, teams can perform cluster health triage, index lifecycle policy management, security configuration, and k-NN vector index optimization through natural language commands.
We walk through real-world scenarios including incident response, setting up RAG pipelines with vector search, and automating ISM policies all without writing a single REST call. Attendees will learn how the MCP standard bridges AI agents to OpenSearch APIs, democratizing cluster management for developers and administrators of all experience levels.
From Broken Silos to Unified Search: Enterprise Search with Agentic AI
Organizations store critical knowledge across dozens of systems — object stores, ticketing platform, messaging platforms, RDMS and many other sources. Users expect a single search experience that finds the right information regardless of where it lives, respects access permissions instantly, and increasingly, answers questions rather than returning document lists. This session presents a five-component architecture for federated enterprise search: per-source indexing for relevance optimization, built-in access control for sub-second security enforcement, two-phase search for accurate facet counts, Reciprocal Rank Fusion for fair cross-source ranking, and an Agentic AI layer that enables conversational, multi-step queries like "Find all open tickets related to the API migration, cross-reference with design docs, and summarize the blockers." Built on Amazon OpenSearch , this architecture is production-ready today. Attendees will leave with a clear blueprint for transforming their enterprise search from keyword-based document retrieval into an intelligent, conversational knowledge discovery platform.
Vector search with Amazon OpenSearch Service
In this session you'll learn how build Retrieval Augmented Generation (RAG) based Gen AI shopping advisor with Amazon OpenSearch Service vector capabilities to. First, you will learn how to build a multimodal search with OpenSearch Service and understand the value proposition compared to the basic lexical search. Then, you will learn how to build a conversational search solution using multimodal search to augment Large Language Model (LLM) prompt with relevant context from both text and images.
Hybrid On-Premises to Cloud Migration with Zero Downtime: Using Apache Iceberg as a Bridge
Migrating petabyte-scale data lakes from on-premises infrastructure to the cloud is one of the most challenging undertakings for enterprise data teams. Traditional migration approaches force organizations to choose between risky "big bang" cutovers or maintaining complex dual systems indefinitely. Apache Iceberg offers a third path: a seamless bridge that enables zero-downtime migration while maintaining data consistency across both environments.This session presents a battle-tested approach for using Iceberg as the foundation for hybrid on-premises-to-cloud migrations. We'll walk through a real-world migration journey, demonstrating how Iceberg's vendor-neutral table format and ACID guarantees enable organizations to operate simultaneously across both environments during the transition period.
Implementing GDPR Right-to-Erasure at Scale with Apache Iceberg: Balancing Compliance, Performance,
The GDPR Right-to-Erasure (Article 17) presents a critical challenge for organizations managing petabyte-scale data lakes: how do you efficiently process millions of deletion requests while maintaining query performance, preserving audit trails for compliance, and avoiding operational disruption? Traditional data lake architectures force teams into impossible tradeoffs—either maintaining tombstone records that bloat storage and slow queries, or physically deleting data and losing the audit trail required by regulators.
Apache Iceberg's row-level delete capabilities and metadata architecture provide a sophisticated solution to this compliance challenge. This session demonstrates production-tested patterns for implementing GDPR-compliant data deletion at scale while maintaining both system performance and regulatory audit requirements.
Machine Learning Driven Search Relevance with Amazon OpenSearch
AI and ML are revolutionizing search relevance by moving beyond keyword matching to semantic understanding. Dense embedding models and cross-encoder rerankers capture meaning, not tokens, while vector search and ANN algorithms surface conceptually relevant results even with zero term overlap. This is transformative in e-commerce, healthcare, and enterprise search where vocabulary mismatch is common.
Learning to Rank (LTR) trains ML models on click-through data and behavioral signals to learn adaptive ranking functions that outperform static rules. Combined with contextual features, LTR delivers personalized relevance at scale.
LLMs and RAG architectures blend search precision with generative reasoning, enabling conversational search, query reformulation, and intelligent answer synthesis. Challenges like model interpretability, bias, and latency drive innovation in distillation, quantization, and hybrid pipelines.
In this session, we cover embedding strategies, hybrid retrieval, LTR-based relevance tuning, RAG patterns, and evaluation frameworks using OpenSearch. Attendees will leave with actionable techniques to build search experiences that truly understand user intent.
Anupa Bhattacharyya
Senior Technical Account Manager, AWS
Philadelphia, New York, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top