AI Engineering Podcast

Niklas Gustavsson, Chief Architect at Spotify, brings a wealth of experience in backend systems and developer experience. He explores Spotify's ambitious journey to scale AI through a standardized, distributed architecture. Topics include the rapid grassroots adoption of coding agents, the delicate balance between team autonomy and standardization, and the evolving role of developers as code-writing time diminishes. Niklas also discusses emerging agent capabilities, like fleet-wide code changes and insights learned from human oversight in AI systems, shaping the future of engineering workflows.

Joe Devon, co-founder of Global Accessibility Awareness Day and tech entrepreneur, dives into the intersection of generative AI and digital accessibility. He discusses how AI can improve captions and audio descriptions while highlighting the inconsistent accessibility of code generated by large models. Joe introduces the AI Model Accessibility Checker to benchmark accessible code production and shares practical steps for better inclusivity. He emphasizes involving users with disabilities in design processes to create truly accessible AI solutions, making it clear that accessibility is a crucial human-rights issue.

Preeti Shukla, a seasoned product and engineering leader with a focus on generative AI and SaaS, dives into the operational challenges of integrating agentic capabilities. She discusses crucial factors like latency, cost control, and data privacy in multi-tenant environments. Preeti emphasizes the importance of starting with internal pilots and outlines frameworks for choosing models and deployment strategies. She also tackles the complexities of evaluation and monitoring in AI systems, offering valuable insights on avoiding confident hallucinations and ensuring reliability.

Craig McLuckie, co-creator of Kubernetes and CEO of StackLock, dives into the pivotal role of the Model Context Protocol (MCP) as the API layer for AI-native applications. He discusses the importance of securing AI agents through optimized MCP deployments and highlights common adoption pitfalls like tool pollution and security risks. Craig also stresses the need for continuous evaluations in stochastic systems and shares insights on ToolHive's innovative approach to orchestration and semantic search for better developer experiences.

Max Beauchemin, a data engineering veteran and creator of Apache Airflow and Superset, discusses his shift to multi-agent development with Agor. He explores the concept of an 'AI-first reflex,' where humans orchestrate tasks while agents accelerate workflows. Max highlights how shifting bottlenecks like code review can be addressed through improved developer experiences and 'context as code.' He introduces Agor’s innovative platform, designed for managing git worktrees and collaborative environments, enabling richer visibility and parallelization in software engineering.

Vinay Kumar, Founder and CEO of Arya.ai and head of Lexsi Labs, dives into the nuances of AI interpretability and alignment. He contrasts interpretability with explainability, highlighting the evolution of these concepts into tools for model alignment. Vinay shares insights on leveraging neuron-level editing for safer LLMs and discusses practical techniques like pruning and unlearning. He emphasizes the need for concrete metrics in alignment and explores the future role of AI agents in enhancing model safety, aiming for advanced AI that is both effective and responsible.

Guillaume de Saint Marc, VP of Engineering at Cisco OutShift, dives into the exciting realm of multi-agent systems. He contrasts rigid workflows with dynamic, self-forming agents that enhance trust in enterprise settings. The discussion touches on the Internet of Agents and the importance of open protocols like A2A and MCP for collaboration. Guillaume highlights the challenges of identity and observability, sharing successes in IT operations. He also introduces Slim, a next-gen communication layer, tailored for efficient agent collaboration.

In this discussion, Will Vincent, a Python developer advocate at JetBrains, dives into the evolution of software engineering alongside AI. He contrasts 'vibe coding' with a more structured 'vibe engineering,' highlighting the importance of collaboration between developers and AI. Will shares practical strategies for utilizing AI tools effectively within IDEs, discusses the role of human oversight in architectural decisions, and addresses the challenges of context loss in code reviews. He emphasizes experimentation and ethical considerations in AI implementation.

Daniel Sodickson, Chief of Innovation in Radiology at NYU Grossman School of Medicine, shares his expertise in AI and medical imaging. He unveils the evolution from linear MRI to deep learning, emphasizing the distinction between upstream AI that influences measurement and downstream AI that interprets images. Their discussion includes the challenges of cross-disciplinary knowledge, ethical implications of decoding brain activity, and innovative concepts like 'imaging without images.' Daniel highlights the necessity of human oversight as AI transforms healthcare and visual understanding.

Andrew Filev, CEO and founder of ZenCoder, shares his expertise on architecting AI-first engineering workflows. He discusses the evolution from simple autocomplete to truly agentic models and emphasizes the importance of context engineering and verification. Filev details ZenCoder's internal playbook, covering human-in-the-loop strategies and test-driven development. He also explores the balance between human control and model autonomy, predicts self-verification trends, and gives insightful lessons on navigating the challenges of building modern coding systems.