Speaker: Fatma Ozcan
Location: Soda Hall, 510
Date: Friday, April 24th, 2026
Time: 12-1 pm PT
Title: Beyond LLMs: Optimizing the Systems Backbone of AI Engines
Abstract:
Large Language Models (LLMs) are redefining analysis across structured and unstructured data, leading to the emergence of two primary architectural paradigms: AI or semantic engines, and data agents. Despite distinct approaches, both architectures encounter pivotal challenges, particularly in optimizing AI operators, agentic pipelines, natural language data interfaces, and AI-powered search. Centrally, embeddings and similarity search are key building blocks. This talk first addresses optimization for semantic operators, presenting an extensive evaluation of proxy models for AI query approximation. Our findings demonstrate a greater than 100x cost and latency reduction for semantic filtering (AI.IF) and significant gains for semantic ranking (AI.RANK). Next, we analyze Filtered Vector Search (FVS), a critical component for semantic search and Generative AI (GenAI) applications within modern database systems. Our core insight is that the optimal algorithm choice is not dictated solely by the computational cost of distance metrics; rather, system-level overheads—encompassing both distance computations and filter operations (such as page accesses and data retrieval)—play a substantial and determinative role. Finally, we discuss the evolution of LLM-driven autonomous agents capable of complex, multi-step tasks across multiple datasets, identifying the discovery of relevant data sources as a major bottleneck and introducing our solution: a metadata reasoner agent.
Speaker Bio: Fatma Özcan is a Principal Engineer at Systems Research@Google. Her current research focuses on GenAI and data management, vector search, platforms and infra-structure for large-scale data analysis, and natural language interfaces to data. Dr Özcan got her PhD degree in computer science from University of Maryland, College Park, and her BSc degree in computer engineering from METU, Ankara. Before joining Google, she was a Distinguished Research Staff Member and a senior manager at IBM Almaden Research Center. She has over 24 years of experience in industrial research, and has delivered core technologies into various IBM and Google products. She is the co-author of the book “Heterogeneous Agent Systems”, and co-author of several conference papers and patents. She is an ACM Fellow and serves on the CRA board of directors, and she is the co-chair of CRA-Industry. She received the VLDB Women in Database Research Award in 2022.