Building the Future of AI Systems: Inside the ODSC AI West Engineering Track

In the age of Software 3.0, AI has become an integral part of how systems are designed, built, and deployed. But building truly reliable, context-aware, and scalable AI systems takes more than model training, as it requires a new kind of engineering discipline.

At ODSC AI West’s AI Engineering Track, leaders from OpenAI, LangChain, Dell, Baseten, Worldware, and others are sharing how the next generation of developers and data scientists are redefining what it means to build with intelligence. From context management and trust frameworks to latency optimization and AI-native CI/CD, these sessions deliver a front-row seat to the architectures, principles, and practices shaping real-world AI systems.

Vibe Coding & The Future of Software Development

Ivan Lourenço Gomes, Front-End Engineer & Technology Instructor, Daweb Schools
Discover how “Vibe Coding” blends traditional development with cutting-edge AI tools like ChatGPT, Claude, Gemini, GitHub Copilot, and Lovable to accelerate the software creation process. This session demonstrates how developers and tech leads can integrate AI into their workflow for faster, higher-quality outcomes — without sacrificing maintainability, architecture, or security. Learn how to treat AI tools as true collaborators that help you build better software, faster.

Context Engineering with LangGraph

Sydney Runkle, Software Engineer, LangChain
Building reliable, long-running AI agents starts with mastering context. This tutorial explores practical techniques for “context engineering” — managing the flow of relevant information across agent runs using LangGraph, an open-source framework for agent orchestration. Attendees will learn strategies for writing, selecting, and compressing context to improve agent performance and consistency across extended interactions.

Context Engineering: A State-of-the-Art Overview

Greg Loughnane, Co-Founder & CEO, AI Makerspace | Chris Alexiuk, Co-Founder & CTO, AI Makerspace | NVIDIA
Context engineering is the next abstraction layer beyond prompt engineering. This workshop unpacks the mental models, taxonomies, and best practices behind context-driven design, showing how to incorporate state, memory, retrieval, and structured outputs into production-grade AI systems. The session culminates in a live build of an agentic, RAG-optimized application to demonstrate how thoughtful context management leads to more powerful and autonomous AI.

How to Bring the Same AI Revolution Software Engineers Have to All Knowledge Workers

Filip Kozera, CEO & Founder, Worldware
Software engineers already leverage AI to automate testing, deployment, and code management. What if every knowledge worker could do the same? This session outlines how to extend AI’s productivity revolution to broader organizational workflows — using AI systems that interpret intent, manage context, and execute tasks while keeping humans in control. Attendees will gain actionable insights into specification-driven task management and the design of AI co-workers that amplify, not replace, human judgment.

Unleashing Enterprise AI: Bridging Innovation and Practicality with Dell AI Factory and NVIDIA

Helen O’Sullivan, AI Solutions Specialist Manager, Dell Technologies
Enterprise AI success requires the right blend of infrastructure, strategy, and execution. This session explores how the Dell AI Factory with NVIDIA helps organizations overcome skill gaps, security concerns, and deployment barriers to scale AI effectively. Attendees will learn best practices for moving from experimentation to production, starting small, and building momentum across industries from healthcare to finance.

Milliseconds Matter: 2x Faster Embedding-based Search, Retrieval, and RecSys in Production

Philip Kiely, Lead Developer Advocate, Baseten
When it comes to embedding-based systems — search, retrieval, recommendation — performance and latency make or break user experience. This session provides a deep dive into optimizing embedding inference at every layer, from runtime and batching to infrastructure and client-side code. Learn how small architectural choices can deliver massive latency improvements, turning prototypes into production-ready, high-speed systems.

AI Engineering Framework for Scalable Impact

Dr. Beju Rao, Entrepreneur, Executive, Board Member, Data Scientist, AI Researcher, and Educator, Amruta, Inc.
Despite its ubiquity, AI’s impact often stalls at the intersection of trust, governance, and integration. This session presents a comprehensive AI engineering framework that addresses these barriers head-on. Built around principles of explainability, governance, and operational alignment, the framework enables transparent, scalable, and responsible AI systems that deliver measurable impact across sectors. Attendees will leave equipped with design patterns that have already driven billions in cost savings and real-world transformation.

Building Reliable AI Products in the Software 3.0 World

Kaustubh Prabhakar, Member of Technical Staff, OpenAI
The leap from prototype to production in the “Software 3.0” era is fraught with fragility. This talk offers a practical playbook for creating reliable, maintainable AI products using modular prompts, AI-native CI/CD flows, and rigorous evals. Learn how to balance rapid iteration with long-term trust and structure, and how to build systems that scale beyond demos — without losing speed or quality.

Context Engineering for AI Code Reviews with MCP, LLMs, and Open-Source DevOps Tooling

David Loker, Director of AI, CodeRabbit
As AI-generated code becomes standard, code review emerges as the next frontier for productivity. This session reveals how CodeRabbit’s context-engineering approach integrates multiple data sources — AST graphs, linters, repo history, and more — to power deep, context-aware AI code reviews. Attendees will see live demos of automated agent-to-agent reviews within IDEs and pull requests, showing how AI can catch subtle bugs, architectural issues, and edge-case errors beyond traditional static analysis.

Engineering the Next Generation of AI Systems

The AI Engineering Track at ODSC brings together the practitioners who are building the foundations of the intelligent systems era — where context, reliability, and human alignment define the frontier. Whether you’re deploying large-scale AI infrastructure, refining prompt pipelines, or architecting agentic workflows, these sessions deliver the hard-won lessons and frameworks that turn promising prototypes into production-grade systems.

Join the engineers who are shaping the future of AI — one framework, one system, and one context window at a time.