SE Radio 698: Srujana Merugu on How to build an LLM App

In this episode of Software Engineering Radio, Srujana Merugu, an AI researcher with decades of experience, speaks with host Priyanka Raghavan about building LLM-based applications. The discussion begins by clarifying essential concepts like generative vs. predictive AI, pre-training vs. fine-tuning, and the transformer architecture that powers modern LLMs. Srujana explains diffusion models and vision transformers, highlighting how multimodal AI is reshaping content creation. The conversation then moves to practical aspects—where LLMs make sense, where they don't, and a decision framework for evaluating use cases. They explore common application patterns such as retrieval-augmented generation (RAG) and agentic architectures, breaking down components like planners, orchestrators, memory, and tools. Key considerations for model selection, evaluation metrics, and safety guardrails are discussed in depth. The episode also touches on prompting strategies, automated prompt optimization, and emerging trends like multi-sensory AI and the "Internet of Senses." Finally, Srujana shares tips on staying current in a fast-moving AI landscape and emphasizes lifelong learning and curated knowledge sources.

In this episode of Software Engineering Radio, Srujana Merugu, an AI researcher with decades of experience, speaks with host Priyanka Raghavan about building LLM-based applications. The discussion begins by clarifying essential concepts like generative vs. predictive AI, pre-training vs. fine-tuning, and the transformer architecture that powers modern LLMs.

Srujana explains diffusion models and vision transformers, highlighting how multimodal AI is reshaping content creation. The conversation then moves to practical aspects—where LLMs make sense, where they don’t, and a decision framework for evaluating use cases. They explore common application patterns such as retrieval-augmented generation (RAG) and agentic architectures, breaking down components like planners, orchestrators, memory, and tools. Key considerations for model selection, evaluation metrics, and safety guardrails are discussed in depth. The episode also touches on prompting strategies, automated prompt optimization, and emerging trends like multi-sensory AI and the “Internet of Senses.” Finally, Srujana shares tips on staying current in a fast-moving AI landscape and emphasizes lifelong learning and curated knowledge sources.

Brought to you by IEEE Computer Society and IEEE Software magazine.

Show Notes

• REACT: Synergizing Reasoning and Acting in Language Models

• Srujana Merugu @ LinkedIn

• Using Human-Like Behaviors in LLMs for Better Prompt Engineering: Exploring the “Lost in the…

• Large Language Models (LLMs) — Top View

• DSPy – Programming not prompting

• ACM Winter School Part 1 Powerpoint

• ACM Winter School – Part 2 Powerpoint

SE Radio Episodes

• SE Radio 582: Leo Porter and Daniel Zingaro on Learning to Program with LLMs

• SE Radio 680: Luke Hinds on Privacy and Security of AI Coding Assistants

• SE Radio 673: Abhinav Kimothi on Retrieval-Augmented Generation

• SE Radio 666: Eran Yahav on the Tabnine AI Coding Assistant

• SE Radio 533: Eddie Aftandilian on GitHub Copilot

• SE Radio 693: Mark Williamson on AI-Assisted Debugging

Original source