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 11 Feb 2026
Duration: 00:51:13
Software engineering has entered a new golden age of large-scale systems, but AI's influence while improving efficiency, cannot replace human creativity and decision-making, and requires oversight and accountability.
AI coding assistants promise speed, but what do they mean for quality, trust, and the architects craft? In this inaugural episode of Next Gen Architec...
The podcast outlines the progression of software engineering through three distinct golden ages, with the current third era characterized by systems operating on a global scale and the widespread use of external platforms and services. Within this context, it examines the growing role of AI in software development, noting that while AI tools can significantly speed up coding and execution, they lack genuine human creativity and the ability to make decisions based on complex, real-world contexts. The discussion underscores the importance of differentiating between design and architecture, with architecture being defined as the set of load-bearing, strategic decisions that maintain the system's coherence and long-term sustainability.
The speaker expresses caution regarding the exaggerated claims about AI's capabilities, warning that overreliance on these tools may lead to a de-skilling of professionals in the field. They emphasize the critical need for human oversight, expertise, and responsibility when utilizing AI-generated code or systems. Drawing parallels between software development and traditional architecture, the podcast highlights that just as buildings require thoughtful human planning, software systems must be guided by human ingenuity. It also points out the ethical, legal, and societal challenges that arise with AI advancements, reinforcing the idea that software development must remain a human-centric discipline. The overall message encourages developers and architects to leverage AI as a means to boost productivity and enable experimentation, while continuing to engage in meaningful, strategic decision-making.
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."