Sharlina Keshava

Domain-specific AI delivers accuracy that is difficult for general models to match. In this session, see how real customers use Amazon Nova Forge to accelerate the path from idea to production..

Domain-specific LLM fine-tuning traditionally demands extensive manual effort. This session explores an innovative multi-agent system built on AWS that continuously improves model performance with minimal human intervention.

Multi-agent AI systems are becoming essential for multi-step production applications, but require specialized models that are small, fast, and cost-effective. This session explores fine-tuning, knowledge distillation, and preference alignment techniques to reduce latency and costs while maintaining performance.

The first hour after a natural disaster is often referred to as the “golden hour," when responders have the highest chance of saving the lives of those effected by the disaster—but it's also when they have least amount of information available to them. In this chalk talk, we walk through different ways machine learning can help accelerate a responder’s understanding of the areas impacted and...