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 6 Jul 2026
Duration: 00:40:44
Examines challenges in AI adoption, system architecture, and kernel security, critiquing Linux and other systems' shortcomings in isolation and scalability, while addressing trade-offs in development speed vs. understanding, hardware limitations, and proposals for improved design and collaboration.
In this episode, Alex Zenla (CTO/Co-founder, Edera) challenges the "laissez-faire" attitude toward modern infrastructure. She promotes "spite-driven d...
The podcast explores challenges and considerations in AI adoption, system architecture, and developer philosophy. It highlights the tension between rapid development using AI-assisted tools (e.g., large language models) and the risks of creating maintainable, well-documented systems. The discussion delves into "spite-driven development," a philosophy rooted in frustration with existing systems, exemplified by critiques of Linuxs imperfections and the need for rethinking operating system design. Adaras Technology is introduced as a project aiming to isolate containers and system images for enterprise use, emphasizing performance and security through custom kernel-level innovations. The narrative also touches on the importance of understanding foundational system layers, such as kernels and hardware, to address security vulnerabilities and avoid over-reliance on abstraction.
A recurring theme is the critique of modern system complexity, particularly the risks of layered architectures that obscure low-level mechanics. The Linux kernels limitationssuch as memory leaks, inadequate isolation, and shared resourcesare examined as critical vulnerabilities that compromise higher-layer security (e.g., Kubernetes clusters). Alternative kernel designs, like Adaras, are proposed to support native containerization and address these shortcomings. The dialogue also addresses GPU usage in AI workloads, emphasizing the mismatch between gaming-optimized hardware and the security needs of machine learning tasks. Finally, the conversation underscores the role of regulation in balancing cybersecurity mandates with privacy concerns, highlighting cross-regional collaborations to shape accountable tech ecosystems. The discussion repeatedly stresses the importance of balancing speed with foundational knowledge, advocating for iterative learning and critical evaluation of AI-generated solutions rather than relying on quick fixes or superficial understanding.
What if you leveraged AI-assisted development to rapidly prototype a secure container system using Adara's "zones" for enterprise use cases?
What if you reimagined the Linux kernel's design to natively support multi-tenancy and process isolation, addressing the limitations of namespaces and cgroups?
What if you built a GPU isolation framework for AI workloads using hardware-specific solutions (e.g., TPUs) instead of repurposed gaming GPUs?
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."