Posts

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Guanhua Wang from Microsoft's DeepSpeed team explains ZeRO++, a system that tackles the communication bottleneck in large-scale LLM training. By quantizing weights and gradients, ZeRO++ reduces communication volume by 4x, leading to training speedups of over 2x, particularly in low-bandwidth and small-batch-size environments.

Beyond Chatbots: How to build Agentic AI systems with Google Gemini // Philipp Schmid

Beyond Chatbots: How to build Agentic AI systems with Google Gemini // Philipp Schmid

A deep dive into the evolution from static chatbots to dynamic, agentic AI systems. Philipp Schmid of Google DeepMind explores how to design, build, and evaluate AI agents that leverage structured outputs, function calling, and workflow orchestration with Google Gemini, covering key agentic patterns and the future of AI development.

How to Build Execution Layers That Don’t Burn Out // Tanmay Tiwari // Agents in Production 2025

How to Build Execution Layers That Don’t Burn Out // Tanmay Tiwari // Agents in Production 2025

A talk on designing a dependable AI execution layer that handles thousands of operations without constant supervision. The system is built to be precise, responsible, and action-oriented, avoiding common LLM pitfalls like burnout, memory bloat, and overthinking.

Underwriting Assist - A Multi Agent System // Somya Rai | Maria Zhang // Agents in Production 2025

Underwriting Assist - A Multi Agent System // Somya Rai | Maria Zhang // Agents in Production 2025

Maria Zhang, CEO of Palona AI, and Somya Rai, Principal AI Engineer at EXL, discuss the architecture, scaling, memory management, and cost optimization of multi-agent systems in their respective domains of restaurants and insurance. They explore practical challenges, such as real-world bottlenecks and regulatory compliance, and share their technical stacks, including LangGraph, Ray, and NVIDIA platforms, for building robust and efficient agentic solutions.

Why You Should Care About Observability in LLM Workflows

Why You Should Care About Observability in LLM Workflows

An inside look at AlwaysCool.ai's journey from simple GPT wrappers to a production-ready agentic infrastructure. This talk covers the evolution from synchronous tools to asynchronous, multi-step flows orchestrated by LangGraph, the critical role of OpenTelemetry for compliance and observability, and the architectural patterns of using FastAPI to serve centralized AI agents.

Why SW Architecture is Mostly Communication • David Whitney, Ian Cooper & Hannes Lowette • GOTO 2025

Why SW Architecture is Mostly Communication • David Whitney, Ian Cooper & Hannes Lowette • GOTO 2025

Three experienced software engineers—Ian Cooper, David Whitney, and Hannes Lowette—deconstruct the evolution of software architecture from a top-down, "ivory tower" practice to a modern, collaborative discipline. They explore the dynamics between emergent and intentional design, the importance of sustainable development over "slash-and-burn" cycles, and how architectural strategies must adapt to organizational scale. The conversation emphasizes that the architect's primary role has shifted to coaching, fostering a shared language, and managing trade-offs, concluding that all significant architectural challenges are ultimately people problems rooted in communication, empathy, and culture.