Episode Summary:

In this episode of Automate or Die Trying, host Wil Ramos sits down with David VonThenen, an AI/ML engineer and systems architect focused on building reliable AI systems that move beyond demos into real-world production.

David shares insights from his background in infrastructure and distributed systems, explaining why strong architecture, observability, and governance are critical when deploying AI at scale. The conversation explores hybrid retrieval approaches beyond simple vector search, the rise of multi-agent AI systems, and the growing need for monitoring and safeguards as AI tools become more autonomous.

For founders, engineers, and technical leaders, David emphasizes a practical approach: design systems carefully, prioritize reliability, and continuously validate AI models in production environments.

Key Takeaways:

• Start with solid system architecture before scaling AI models
• Hybrid retrieval strategies often outperform pure vector search
• Multi-agent architectures allow modular, scalable AI workflows
• Observability and governance are critical for production AI systems
• Adversarial prompts highlight the need for strong safeguards
• Infrastructure design still matters as much as model quality

Connect with David VonThenen:

• LinkedIn: https://linkedin.com/in/davidvonthenen
• GitHub: https://github.com/dvonthenen
• Twitter/X: https://twitter.com/dvonthenen
• Personal Website: https://davidvonthenen.com

Listen Now & Subscribe:

Apple Podcasts, Spotify, Amazon Music, or find us wherever you get your podcasts.

Powered by cybersecurityprivacy.com

Automate or Die Trying empowers leaders to adopt AI securely, move faster with confidence, and transform the future of work.