Building an AI Platform: Memory, Tools, Guardrails, Observability & Shipping a Production Agent | Dewang Sultania
Listen to or watch on your favorite platform
Show Notes
Dewang Sultania joins Alexey Grigorev for the second conversation with the authors of Designing AI Systems. They discuss the platform services needed to move from an LLM chatbot to an agent that takes actions: session memory, tool integration, execution policies, observability, and deployment.
Links:
Timestamps
Timestamps coming soon...
About the Guests
Dewang Sultania
Dewang Sultania is a Senior Machine Learning Engineer at Netflix, where he designs scalable systems for multimodal generative AI, diffusion models, and video processing. Previously at Adobe, he built production systems for large language models, including data pipelines, fine-tuning, retrieval-based systems, and prompt engineering. He also helped design the platform infrastructure used to deploy large language models across Adobe’s product suite.
