9 Nov 2026 Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM
WebAssembly and Tornado VM enable efficient local inference, while LLMD optimizes distributed GPU usage and semantic routing for on-premises AI deployment.
More Podcasts by InfoQ episodes

Published 26 Jan 2026
Duration: 00:57:59
This podcast delves into the complexities of architecture in startup environments, discussing flexibility, communication, decision-making, and scalability in the face of limited information and evolving business needs.
In this podcast Michael Stiefel spoke with David Gudeman about software architecture for startups. The discussion starts by illuminating how to make d...
The podcast explores the complexities of architectural decision-making in startup environments, where flexibility and adaptability are essential due to frequent changes in direction and limited resources. It emphasizes the importance of aligning technical strategies with business objectives by understanding client needs and making informed choices despite uncertainty. The panel discusses how rigid planning can hinder progress, and instead, advocates for pragmatic approaches that allow for iteration and evolution as the startup grows.
Key points include the benefits of reusing existing systems to save time and reduce risk, as well as the architect's role in ensuring that the system remains scalable and maintainable over time. The discussion also covers the challenge of balancing technical precision with the ambiguity often found in early-stage startups, and the value of involving architects early in the development process to guide design decisions. The panel shares real-world examples of system redesigns aimed at improving flexibility and managing shifting requirements, emphasizing the need to avoid overengineering while still supporting long-term product success.
The narrative reflects on the trade-offs between building custom solutions from scratch and leveraging existing platforms, with a focus on creating practical, sustainable architectures. The insights drawn from personal experiences highlight the necessity of clear communication between technical and business teams, as well as the importance of making decisions that directly contribute to the startup's core value. Overall, the podcast underscores the idea that successful architecture in startups requires a balance of foresight, pragmatism, and the ability to respond quickly to change.
9 Nov 2026 Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM
WebAssembly and Tornado VM enable efficient local inference, while LLMD optimizes distributed GPU usage and semantic routing for on-premises AI deployment.
2 Nov 2026 Educating an Architect: A Conversation with Luca Mezzalira
Architects must evolve from technical designers to social-technical enablers, using domain-driven design to balance AI automation with human oversight in core systems.
12 Oct 2026 What Does It Really Mean To Program With AI: A Conversation with Joy Ebertz
"Explores software architects' evolving role in balancing technical and business challenges, AI's impact on modular architectures, risks of automation, and the need for human oversight in AI-assisted development."
5 Oct 2026 Future Cybersecurity: Hardware Memory Safety, Automated Governance and Post-Quantum Cryptography
"Challenges and advancements in AI, security, and software development are discussed, emphasizing governance, open-source maintenance, hardware security, automation, and regulatory compliance like the EU's Cyber Resilience Act, alongside post-quantum cryptography and AI's dual role in security."
28 Sept 2026 The AI Revolution Fails Without Psychological Safety For Developers: A Conversation with Erin Doyle
"Software architects must adapt to AI-driven shifts in system design, balancing automation with human oversight, team alignment, and ethical considerations in modern development."