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 4 Mar 2026
Duration: 00:52:05
Generative AI is transforming software architecture, requiring a shift from incremental tool adoption to systemic thinking and governance to manage unpredictability and mitigate risks.
This conversation explores why generative AI is not just another automation layer but a shift into autonomy. The key idea is that we cannot retrofit A...
The podcast explores the complexities of integrating generative AI into modern software architecture, highlighting the shift from incremental tool adoption to systemic redesign. It emphasizes the risks of hallucination and drift when embedding AI into procedural systems, arguing that retrofitting AI without rethinking governance and architecture can lead to unpredictable outcomes. The discussion underscores the need to move away from rigid control mechanisms toward boundary management, where clear goals, constraints, and seven defined "seams" (interfaces and governance points) are established to contain AI agents and ensure alignment with organizational objectives.
Key challenges include managing emergent behaviors in multi-agent systems and adapting guardrails as systems scale. The podcast stresses the importance of redefining architectural principles to accommodate AI autonomy, balancing innovation with robust governance frameworks. It advocates for proactive strategies to mitigate risks while enabling systems that are both scalable and adaptive, ensuring that AI integration enhances rather than undermines stability and functionality in complex software environments.
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."