Kyle Bunting
CEO, Echte LLC
Monument, Colorado, United States
Actions
Kyle Bunting is a CEO, data strategist, and AI engineering leader with 27+ years of experience designing and delivering modern data platforms, cloud architectures, and enterprise AI solutions. He specializes in helping organizations operationalize data and AI responsibly, securely, and at scale. As CEO of Echte LLC, Kyle leads a consultancy focused on building robust data engineering foundations, scalable AI systems, and cloud‑native architectures that drive measurable business outcomes. He works directly with organizations to modernize legacy environments, implement intelligent automation, and establish governance frameworks that support long‑term, sustainable AI adoption.
As a Microsoft Certified Trainer, Kyle regularly presents at conferences and delivers workshops on AI engineering, cloud architecture, and data platform modernization. His career spans insurance, healthcare, finance, and defense, where he has guided technical execution, solution architecture, and strategic consulting for complex, high‑stakes environments.
Kyle holds an M.B.A. from Purdue University’s Krannert School of Management, a B.A. in Psychology from Purdue, and an A.A.S. in Computer Programming & Network Engineering from ECPI College of Technology.
Area of Expertise
Topics
Boosting RAG Accuracy: Advanced Techniques for Better AI Responses
Retrieval-Augmented Generation (RAG) has become the go-to strategy for grounding large language models with contextual data in AI-driven applications. Yet, despite its promise, RAG often struggles with accuracy, retrieving irrelevant or suboptimal results that dilute the effectiveness of AI-generated responses. In this session, we explore cutting-edge techniques to elevate RAG accuracy, including semantic reranking for smarter relevance scoring, Graph RAG to strengthen contextual reasoning through knowledge graphs, and optimized chunking and query transformations to enhance retrieval precision. By implementing these strategies, developers can significantly reduce hallucinations and create AI systems that deliver highly reliable and contextually grounded answers.
Generative AI in the Enterprise
"Generative AI is easy!" Just ask a question, and you get an answer. Simple, right? While individuals can easily engage with AI, enterprises face a far more complex reality. To deploy Generative AI securely, at scale, and with extensibility, organizations must navigate a vast ecosystem of infrastructure, including servers, APIs, agents, tools, data sources, prompts, embedding models, vector databases, and more. This session breaks down the real challenges of enterprise AI adoption, from compliance and data security to retrieval precision and system performance at scale. We'll explore why traditional RAG struggles with massive data volumes, how Knowledge Graphs enhance AI retrieval, and how multi-LLM architectures integrate with orchestrators like LangChain and Semantic Kernel across diverse data sources.
Using Data Pipelines to Process Batch and Real-Time Data
Data pipelines funnel data from multiple sources, both batch and streaming, into a centralized location to facilitate the summarization and analysis of those data. Big data analytics is the process of combining large and diverse data sets with AI to create actionable insights. In this session, we will examine using Azure Databricks, Azure Data Factory, and various serverless technologies in Azure to create flexible and powerful data pipelines for AI.
Perform data engineering on Azure
This two-day workshop is an in-depth review of the Azure data platform and tools you can use to perform data engineering tasks. Data engineering is a relatively new role in today's data-driven organizations. In this course, we define the role of the data engineer on Azure and walk you through the most common challenges and tasks they perform. Learn through hands-on labs, presentations, and Q&A sessions with data engineering experts.
Bring a laptop and power cord since there are several hands-on labs as part of this workshop.
On the RAGged Edge: Semantic Operators, Knowledge Graphs, and Smarter Retrieval in PostgreSQL
The future of RAG isn’t just dense vectors. It's deep semantics and graph reasoning. This session shows how Azure Database for PostgreSQL brings GenAI workloads to life using semantic operators and integrated LLM capabilities. You’ll learn to extract structure from messy text, perform semantic re-ranking of content, and assess the truthfulness of natural language statements. Then, take it further by building knowledge graphs with Apache AGE to support precise, context-aware retrieval. By the end, you’ll have a full pattern for next-gen retrieval in PostgreSQL using tools already in your data stack.
Migrating from a relational to a NoSQL cloud database
The volume, velocity, and variety of data being created and consumed continues to change the way we approach storing and processing data. For the growing world of Big Data, traditional relational database systems simply don’t fit anymore. NoSQL databases can help. In this session, we look at approaches for migrating from an RDBMS to a cloud-hosted NoSQL database.
Intelligent Data Engineering on Azure - Part 1
This two-day workshop is an in-depth review of the Azure data platform and tools you can use to perform data engineering tasks. Data engineering is a relatively new role in today's data-driven organizations. In this course, we define the role of the data engineer on Azure and walk you through the most common challenges and tasks they perform. Learn through hands-on labs, presentations, and Q&A sessions with data engineering experts.
Dive into the world of data engineering on Azure
During this two-day workshop, we conduct a comprehensive review of the roles and responsibilities of data engineers within the context of the Azure Intelligent Data Platform for the purpose of developing solutions for Generative AI workloads. The workshop provides an in-depth exploration of the essential tools and techniques required to effectively execute data engineering tasks pertinent to advanced AI scenarios. The course explores the function of data engineers on Azure, addressing prevalent challenges and tasks encountered in this domain. The workshop encompasses practical hands-on labs, informative presentations, and interactive Q&A sessions facilitated by proficient and experienced data engineering specialists, instilling confidence in your learning journey.
Participants are kindly reminded to bring their laptops and power cords, as the workshop will feature multiple hands-on labs necessitating these resources.
Building & Integrating Custom Skills into an Azure Cognitive Search AI Enrichment Pipeline
Knowledge mining is an emerging category in AI, which refers to the orchestration of a series of AI services to uncover latent insights in vast amounts of data. Custom skills provide a mechanism for developers to leverage customized rules and logic specific to their industry or organization. By integrating custom skills into an Azure Cognitive Search enrichment pipeline, teams can use the machine learning models they develop to enrich their data further. In this session, we examine the Web API custom skill interface for building custom skills and connecting those to an enrichment pipeline to benefit from the power of custom AI in Azure Cognitive Search.
Knowledge Mining with Azure Cognitive Search
Knowledge mining is a technique for using AI to extract additional metadata from images, blobs, and other unstructured data. In this session, we review the process for intelligently extracting information from opaque documents using an Azure Cognitive Search enrichment pipeline. Pre-built and custom cognitive skills are used to enrich the search index, making the content more searchable and usable.
Supercharging GenAI Apps with Azure Database for PostgreSQL
GenAI is driving a shift in the types of applications we build, enabling more intelligent automation, dynamic content generation, and natural language interactions. Microsoft is amplifying these capabilities by embedding GenAI directly into Azure Database for PostgreSQL through the Azure AI extension, giving developers seamless access to powerful AI models within their applications. In this session, we’ll explore how you can leverage these built-in AI features to enhance app intelligence, streamline workflows, and unlock new possibilities for innovation, without needing external AI infrastructure.
Build AI apps with Azure Database for PostgreSQL
The Azure AI extension enables Azure AI Services and Azure OpenAI capabilities to be integrated directly into Azure Database for PostgreSQL. In this session, we explore how the azure_ai extension can be used to build AI applications with Azure Database for PostgreSQL Flexible Server. Using the azure_ai extension allows us to take advantage of large language models (LLMs) and generative AI directly from the database. LLMs are designed to understand and generate human-like language output and are known for their ability to perform a wide range of tasks related to understanding and generation of natural language. Generative AI has a wide range of benefits for data-driven apps, including semantic search, recommendation systems, and content generation, such as summarization, among many others.
Denver Dev Day | Developer's Conference | June 2025 Sessionize Event
Devintersection and next GenAI Conference Sessionize Event
Microsoft Azure + AI Conference Spring 2022 Sessionize Event
Microsoft Azure + AI Conference Spring 2022 Sessionize Event
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