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 16 Feb 2026
Duration: 00:35:19
This podcast outlines the transformation of financial services software architecture to modern, event-driven, and microservices-based models, facilitated by tools like Kafka and AI, while addressing key challenges such as legacy system integration, security, and compliance.
In this episode, Thomas Betts chats with Muzeeb Mohammad about building event-driven microservices for financial systems. The discussion covers some o...
The podcast examines the transition in financial services from traditional monolithic and mainframe systems to more modern, event-driven, and microservices-based architectures. These new architectures leverage tools like Kafka and message queues to enable asynchronous processing, improve service-level agreement (SLA) performance, and support faster deployment cycles by decoupling backend processes. A hybrid strategy is outlined to integrate legacy mainframe systems with emerging distributed technologies, involving the development of a System of Reference that will eventually replace the mainframe as the primary data source. This approach is supported by observability tools and Change Data Capture to maintain data consistency and ease migration.
The discussion also explores the potential of AI in financial services, citing examples such as anomaly detection and dynamic security policies in proof of concept implementations. These applications demonstrate AI's potential to enhance system reliability and customer experience. Security and compliance remain central to modernization efforts, with particular attention given to the handling of personal identifiable (PI) data and adherence to PCI standards. The transformation also involves a cultural shift in engineering practices, with greater emphasis on end-to-end infrastructure and security management responsibilities.
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."