Abstract: While Large Language Models have advanced rapidly, building reliable production-grade systems around them remains a complex engineering challenge. In this webinar, Anni Chen introduces a systems-driven framework for deploying LLMs in real-world environments. The session explores how to identify high-impact use cases, design retrieval-augmented architectures, navigate latency and cost trade-offs, and establish continuous evaluation and feedback loops. Drawing on experience with large-scale deployments, the talk emphasizes disciplined engineering, responsible AI practices, and scalable infrastructure. It offers a practical blueprint for turning powerful models into dependable, measurable business systems.
Presenter: Anni Chen is a Tech Lead at Amazon, where she builds production-scale generative AI systems for personalized user experiences. She co-initiated a patent-pending LLM initiative focused on scalable recommendation generation and user memory infrastructure.
She serves as an invited peer reviewer for leading IEEE, ACM, and Elsevier journals, evaluating cutting-edge research in machine learning and applied AI. Her perspective on generative AI has been featured in Business Insider.
Anni’s work bridges research and production, advancing reliable, real-world LLM systems from experimentation to deployment.
