SE Radio 703: Sahaj Garg on Low Latency AI

In this episode, Sahaj Garg, CTO of wispr.ai, joins SE Radio host Robert Blumen to talk about the challenges of building low-latency AI applications. They discuss latency's effect on consumer behavior as well as interactive applications. The conversation explores how to measure latency and how scale impacts it. Then Sahaj and Robert shift to themes around AI, including whether "AI" means LLMs or something broader, as they look at latency requirements and challenges around subtypes of AI applications. The final part of the episode explores techniques for managing latency in AI: speed vs accuracy trade-offs; speed vs cost; latency vs cost; choosing the right model; reducing quantization; distillation; and guessing + validating. Brought to you by IEEE Computer Society and IEEE Software magazine.

Derick Schaefer, author of CLI: A Practical Guide to Creating Modern Command-Line Interfaces, talks with host Robert Blumen about command-line interfaces old and new. Starting with a short review of the origin of commands in the early unix systems, they trace the evolution of commands into modern CLIs. Following the historic rise, fall, and re-emergence of CLIs, they consider innovative examples such as git, github, WordPress, and warp. Schaefer clarifies whether commands are the same as CLIs and then discusses a range of topics, including implementation languages, packages in the golang ecosystem for CLI development, CLIs and APIs, CLIs and AIs, AI tooling versus MCP, the object-command pattern, command flags, API authentication, whether CLIs should be stateless, and output formats - json, rich text. Brought to you by IEEE Computer Society and IEEE Software magazine.

Max Geurnsey III and Luniel de Beer, co-authors of the book Ready: Why Most Software Projects Fail and How to Fix It, discuss the concept of readiness in software engineering with host Brijesh Ammanath. Although Agile workflows and technical practices help delivery, many software efforts still struggle to achieve desired outcomes. Rework, shifting requirements, delays, defects, and mounting technical debt can plague software delivery and impede or altogether halt progress toward goals. The problem is often that implementation begins prematurely, before the team is properly set up for success. A strict system of explicit readiness work and gating, called Requirements Maturation Flow (RMF), has the potential to solve this problem in an SDLC-independent way. Teams that adopt RMF can dramatically improve progress toward real goals while reducing stress on engineering teams. In this episode, Max and Luniel deep dive into RMF and explain its foundational pillars. Brought to you by IEEE Computer Society and IEEE Software magazine.

Mojtaba Sarooghi, a Distinguished Product Architect at Queue-it, speaks with host Jeremy Jung about virtual waiting rooms for high-traffic events such as concerts and limited-quantity product releases. They explore using a virtual queue to prevent overloading systems, how most traffic is from bots, using edge workers to reduce requests to the customer's origin servers, and strategies for detecting bots in cooperation with vendors. Mojtaba discusses using AWS services like Elastic Load Balancing, DynamoDB, and Simple Notification Service, and explains why DynamoDB's eventual consistency is a good fit for their domain. To explain the approach, he walks us through how his team resolved an incident in which a traffic spike overloaded their services. Brought to you by IEEE Computer Society and IEEE Software magazine.

In this episode, Benjamin Brial, CEO and co-founder of Cycloid, speaks with host Sriram Panyam about internal developer platforms (IDPs) and internal developer portals. The conversation explores how these platforms address the growing challenges of DevOps scalability, multi-cloud complexity, and cloud waste, all of which organizations face as they grow. Benjamin begins by framing the core problems that IDPs solve: DevOps struggling to scale beyond small teams, the complexity of managing hybrid environments across on-premises, public cloud, and private cloud infrastructure, and the significant issue of cloud waste (averaging 35-45% according to major analysts). IDPs can serve as a bridge between DevOps teams and developers, providing access to tools, cloud resources, and automation for users who aren't DevOps or cloud experts. The technical discussion covers essential IDP components including service catalogs, versioning engines, platform orchestration, asset inventory, and FinOps/GreenOps modules. The episode concludes with Benjamin's practical advice: organizations should focus on understanding their specific pain points rather than following market trends, starting with simple use cases such as landing zones before building complex solutions, and adopt a GitOps-first approach as the foundation for any IDP implementation. Brought to you by IEEE Computer Society and IEEE Software magazine.

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.

Philip Kiely, software developer relations lead at Baseten, speaks with host Jeff Doolittle about multi-agent AI, emphasizing how to build AI-native software beyond simple ChatGPT wrappers. Kiely advocates for composing multiple models and agents that take action to achieve complex user goals, rather than just producing information. He explains the transition from off-the-shelf models to custom solutions, driven by needs for domain-specific quality, latency improvements, and economic sustainability, which introduces the engineering challenge of inference engineering. Kiely stresses that AI engineering is primarily software engineering with new challenges, requiring robust observability and careful consideration of trust and safety through evals and alignment. He recommends an approach of iterative experimentation to get started with multi-agent AI systems. Brought to you by IEEE Computer Society and IEEE Software magazine.

Flavia Saldanha, a consulting data engineer, joins host Kanchan Shringi to discuss the evolution of data engineering from ETL (extract, transform, load) and data lakes to modern lakehouse architectures enriched with vector databases and embeddings. Flavia explains the industry's shift from treating data as a service to treating it as a product, emphasizing ownership, trust, and business context as critical for AI-readiness. She describes how unified pipelines now serve both business intelligence and AI use cases, combining structured and unstructured data while ensuring semantic enrichment and a single source of truth. She outlines key components of a modern data stack, including data marketplaces, observability tools, data quality checks, orchestration, and embedded governance with lineage tracking. This episode highlights strategies for abstracting tooling, future-proofing architectures, enforcing data privacy, and controlling AI-serving layers to prevent hallucinations. Saldanha concludes that data engineers must move beyond pure ETL thinking, embrace product and NLP skills, and work closely with MLOps, using AI as a co-pilot rather than a replacement. Brought to you by IEEE Computer Society and IEEE Software magazine.

Dave Thomas, author of The Pragmatic Programmer, The Manifesto for Agile Software Development, Programming Ruby, Agile Web Development with Rails, Programming Elixir, Simplicity, and co-founder of the Pragmatic Bookshelf, speaks with SE Radio host Gavin Henry about building infrastructure for eBooks. They discuss what an eBook is, the various formats, what infrastructure is needed to build them, how an author writes an book, the history of the Pragmatic Bookshelf, how they have evolved, how to handle links within eBooks, why humans are so important in the writing process, and why AI can help with your writing -- once you've written your content. Thomas discusses PDFs, eBooks, Mobi files, ePub files, CI/CD pipelines, WYSWYG, Markdown files, Pragmatic Markup Language, embedding code, AI agents, images, printing PDFs, JVMs, Java, jRuby, and how Markdown won the plain text writing format wars. Brought to you by IEEE Computer Society and IEEE Software magazine.

Jennings Anderson, a Software Engineer with Meta Platforms, and Amy Rose, the Chief Technology Officer at Overture Maps Foundation, speak with host Gregory M. Kapfhammer about the Overture Maps project, which creates reliable, easy-to-use, and interoperable open map data. After exploring the foundations of geospatial information systems, Gregory and his guests dive deep into the implementation of Overture Maps through features like the Global Entity Reference System (GERS). In addition to discussing the organizational structure of the Overture Maps Foundation and the need for a unified database of geospatial data, Jennings and Amy explain how to implement applications using data from Overture Maps. Brought to you by IEEE Computer Society and IEEE Software magazine.