Welcome to Data Architecture Elevator, a vibrant podcast produced by Agile Lab (www.agilelab.it). Join our expert architects for an engaging hour of friendly chat as they explore the hottest topics in the data architecture space. Each episode dives into innovative solutions, industry trends, and practical insights to elevate your understanding of data architecture. Whether you’re a seasoned pro or just curious, hop on and ride the elevator with us to new heights in data innovation!
Welcome to another Data Architecture Elevator podcast! Today's discussion is hosted by Paolo Platter supported by our experts Antonino Ingargiola and Irene Donato.
In this episode, we explore effective strategies for optimizing large language models (LLMs) for inference tasks with multimodal data like audio, text, images, and video.
We discuss the shift from online APIs to hosted models, choosing smaller, task-specific models, and leveraging fine-tuning, distillation, quantization, and tensor fusion techniques. We also highlight the role of specialized inference servers such as Triton and Dynamo, and how Kubernetes helps manage horizontal scaling.
Don't forget to follow us on LinkedIn! Enjoy!
1 Apr 2025
Agentic AI, Model Context Protocol and Data Products
Welcome to another episode of Data Architecture Elevator, hosted by Paolo Platter (https://www.linkedin.com/in/paoloplatter/) and featuring Antonino Ingargiola (https://www.linkedin.com/in/antonino-ingargiola/) and Antonio Murgia (https://www.linkedin.com/in/antonio-murgia/).
The conversation explores how Model Context Protocol (MCP), introduced by Anthropic, enables interoperability between LLM-based agentic applications and external systems through a standardized client-server model. In this setup, agents (LLM clients) discover and invoke tools exposed by MCP-compliant servers. This protocol decouples integration logic, allowing systems to interoperate without custom code. The discussion then applies MCP to data products in a data mesh architecture, where output ports (data access), observability ports (data quality and freshness), and control ports (operations) can be exposed as tools via MCP. This allows agents to autonomously query data, evaluate its quality, and even trigger operational commands like restarts or compliance actions. Enjoy it :)
6 Mar 2025
Data Privacy in the Age of Large Language Models
Welcome to another episode of Data Architecture Elevator Podcast!
Today we'll tackle another hot topic: Data Privacy related to Large Language Models. Large language models (LLMs) have changed the way we interact with technology, enabling more natural conversations, automating tasks, and generating human-like responses. But as the saying goes, with great power comes great responsibility. The intersection of LLMs and privacy raises crucial questions: How do these models process and store user data? What safeguards exist to prevent unintended data retention? And what steps can businesses take to ensure compliance with data protection regulations? Join the discussion with our host Paolo Platter and our guests Antonio Murgia, Antonino Ingargiola and Irene Donato.
Don't forget to follow us on LinkedIn!
Enjoy!
3 Mar 2025
Agents vs Tools: Spot the differences!
Welcome to a new episode of Data Architecture Elevator Espresso with an in-depth analysis of agents and tools in the field of Agentic AI. In this episode, hosted by Antonio Murgia and with our dear guest Irene Donato, we'll explore two concepts often used interchangeably but with crucial distinctions. What are the differences between AI Agents and AI Tools? Understanding these differences is vital for businesses and technologists looking to leverage AI effectively. Enjoy!
20 Feb 2025
Espresso - WASM and UDF
Hello there!
Today we'll explore the usage of WebAssembly to streamline User Defined Functions. We're going to do that with the help of our guest Andrea Fonti and our dear host Antonio Murgia. User-defined functions (UDFs) have long been a powerful tool for extending database and query engine capabilities. From traditional relational databases to modern big data platforms like Hive and Spark, UDFs enable developers to introduce custom logic tailored to their specific needs. However, the existing methods of implementing UDFs often come with significant constraints: rigid language requirements, security concerns, and performance bottlenecks. WebAssembly (Wasm) is a technology that promises a more flexible, secure, and efficient approach to UDF development.
Don't forget to follow us on LinkedIn! Enjoy :)
12 Feb 2025
Agentic AI
We're thrilled to start a new podcast with one of the hottest topic so far: Agentic AI.
From autonomous systems to ethical dilemmas, from AI-driven creativity to its impact on business, we dive into this intriguing theme with our host Paolo Platter engaging and interviewing our guests Antonio Murgia (Data Architect) and Antonino Ingargiola (AI Architect) .
Enjoy!
17 Dec 2024
Data Privacy and Crypto-Shredding
Imagine a world where your sensitive data vanishes—not just deleted, but utterly irretrievable. That’s the magic of crypto-shredding: a technique where encryption keys are destroyed, rendering the data useless, forever.
🔑 Why does this matter?
✅ No keys = No access.
✅ It's clean, efficient, and a data security mic drop.
✅ Essential for GDPR compliance, sensitive records, and peace of mind.
In this episode, we break it down:
What crypto-shredding is (and isn’t).
Real-world use cases and myths busted.
When you should consider it for your business.
Hosted by Paolo Platter, we will dive into Data Privacy and Crypto-Shredding with the help of Francesco Valentini and Antonio Murgia.
12 Dec 2024
Espresso - Data Science and Data Engineering
Data architecture expert Pietro Peterlongo shares insights into the intersections between Data Scientists and Data Engineers, highlighting the importance of collaboration for successful data-driven projects.
3 Dec 2024
Espresso - MLOps
Antonio Murgia explores MLOps best practices with guest Antonino Ingargiola, ensuring reliable and efficient deployment of machine learning models in production.
22 Nov 2024
Data Contracts
Data architecture experts Antonio Murgia & Ugo Ciracì join Paolo Platter to reveal how data contracts ensure trust, accountability, and scalability in modern data management.
14 Nov 2024
Espresso - FinOps
Here's a brand new episode of the Data Architecture Elevator Espresso! Today we discuss an intro to FinOps with a special guest in the FinOps: Ugo Ciracì.
Ugo is the author of the article that addresses the FinOps discipline in details: you can read it at https://www.agilelab.it/blog/finops-architecture-for-data-products. This episode is hosted by our Antonio Murgia.
Don't forget to follow us on LinkedIn!
7 Nov 2024
Espresso - Platform Engineering
Welcome to another episode of Data Elevator Architecture Espresso, 20 minutes of condensed knowledge shared by our Experts! Today we delve into Platform Engineering: a clear definition, practices and insights on this hot topic directly from an expert like Andrea Novara hosted by our dear Antonio Murgia.
Don't forget to follow us on LinkedIn!
29 Oct 2024
Espresso - Data Streaming
Welcome to the new format Espresso, 20 minutes of condensed knowledge shared by our Experts! This episode features a talk and insights about Data Streaming and security applied to Kafka.
Today's guest is:
Andrea Fonti
with our host
Antonio Murgia
Don't forget to follow us on LinkedIn!
22 Oct 2024
Privacy
Episode 4 of Data Architecture Elevator podcast: insights about Data Privacy. Discussion about impact on practices, technologies while assuring compliance.
Today's guests are:
Antonio Murgia
Francesco Valentini
with our host Paolo Platter.
Don't forget to follow us on LinkedIn!
26 Sept 2024
Accelerated Analytics
Episode 3 of Data Architecture Elevator podcast: some insights about Accelerated Analytics. Definition, applicability, technology and relations with the Data Engineer role.
Today's guests are:
Antonio Murgia
Ugo Ciracì
Francesco Valentini
with our dear host Paolo Platter.
Don't forget to follow us on LinkedIn!
27 Aug 2024
Data Streaming
In this episode of Data Architecture Elevator we're discussing Data Streaming, what are its main advantages and the challenges that companies face when adopting it.
24 Jul 2024
Data Platforms
In this episode of Data Architecture Elevator we're discussing Data Platforms, what's their relation with Data Management practices and strategies.
Podcast Authority Score: 9 / 100
A composite of feed quality, social presence, YouTube performance and engagement. Read the methodology.
Quality
18
Social presence
0
YouTube
0
Engagement
0
Host of Data Architecture Elevator?
Claim your podcast to manage its listing and keep your show details accurate.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show Podcast research with Pod Engine
