Constrained Autonomy: AI Models, Memory, and Retrieval at the Edge
This event explores the engineering challenges of deploying AI to constrained physical systems and edge devices, focusing on AI models, memory, and retrieval. It covers local LLM inference economics, agentic memory design, and embedded vector search for offline autonomy, targeting engineers in robotics, applied ML, and embedded systems.
Constrained Autonomy: AI Models, Memory, and Retrieval at the Edge
This event explores the engineering challenges of deploying AI to constrained physical systems and edge devices, focusing on AI models, memory, and retrieval. It covers local LLM inference economics, agentic memory design, and embedded vector search for offline autonomy, targeting engineers in robotics, applied ML, and embedded systems.
This session addresses the engineering difficulties of implementing AI on edge devices and constrained physical systems. It will explore the economics of local LLM inference, the creation of agentic memory systems for ongoing state management, and the use of embedded vector search for offline autonomy. The event is intended for engineers in robotics, applied machine learning, and embedded systems. Attendees can expect discussions on building robust agentic behavior that operates without relying on cloud infrastructure.
Listed on Luma. Full details and registration on Luma
Summary AI-generated; content may not always be accurate.