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 9 Mar 2026
Duration: 00:38:25
Scaling technology initiatives from MVP to production requires a shift from project-based approaches to sustainable growth, overcoming legacy systems, AI integration, and cultural barriers.
In this episode, Thomas Betts and Sam McAfee discuss how AI hype is reshaping organizational behavior, why many companies struggle with experimentatio...
The podcast explores the challenges of scaling technology initiatives from minimum viable products (MVPs) to full production, highlighting the shift required from short-term project-based approaches to long-term sustainable growth. Key obstacles include legacy systems that hinder progress, the difficulty of integrating AI into products without robust infrastructure or validated customer needs, and the cultural and structural barriers within large organizations that stifle innovation. These barriers are compounded by misaligned investment priorities, where early-stage experimentation is often overshadowed by a focus on immediate results, and the lack of "startup thinking" that emphasizes iterative development and continuous customer feedback.
The discussion underscores the importance of fostering psychological safety, mindful leadership, and an experimental mindset to navigate uncertainty and drive innovation. It also addresses the complexities of AI's impact on software development, emphasizing the need for new tools, enhanced security frameworks, and a balance between automation and human oversight. The podcast draws parallels to past technological trends, cautioning against superficial AI implementations that fail to align with real customer needs. Instead, it advocates for a deliberate, customer-centric approach to AI adoption, ensuring that technological advancements are grounded in practical use cases rather than hype.
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."