Implementing Gen AI in Practice


Generative AI has taken over the world by storm, but building Gen AI applications for production comes with a unique set of challenges. Questions around cost performance, risk, simplifying implementation for production, setting guardrails, adding automation where possible and leveraging CI/CD for ML all become even more important when Gen AI is involved.

In this talk, we'll cover the necessary foundations for Gen AI use cases and how to build an ‘AI Factory’ that will enable you to continuously roll out new Gen AI applications, based on 3 real world examples:
1. Creating a Virtual SME (Subject Matter Expert)
Fine-tuning an LLM to become a subject matter expert on your area of choice, creating an app that can supplement your marketing, customer service or support channels.
2. Using Gen AI to build a Smart Customer Call Center Analysis App
Building an app that analyzes customer calls at scale, providing information such as the call topic and whether the customer's issue was successfully resolved, and including important aspects such as PII (Personal Identifiable Information) removal.
3. Building an Intelligent Chatbot with LLMs
Building an intelligent chatbot for customer service, to use as a virtual agent, or for eneral Q&A, including application information, validation and stateful classification.
Creating a chatbot that can understand the nature of the request, extract the right parameters, route it accordingly to the relevant application, validate and monitor it, format and save its state for the next inquiry.

Through all of these examples, I will provide best practices on how to build a reproducible process for rapid development; deployment while keeping costs low, addressing modularity, safety and production readiness.


Yaron Haviv is a serial entrepreneur who has been applying his deep technological experience in AI, cloud, data and networking to leading startups and enterprises since the late 1990s. As the Co-Founder and CTO of Iguazio, Yaron drives the strategy for the company’s MLOps platform and led the shift towards the production-first approach to data science and catering to real-time AI use cases. He also initiated and built Nuclio, a leading open source serverless framework with over 4,000 Github stars and MLRun, a cutting-edge open source MLOps orchestration framework. 

Prior to co-founding Iguazio in 2014, Yaron was the Vice President of Datacenter Solutions at Mellanox (now NVIDIA - NASDAQ: NVDA), where he led technology innovation, software development and solution integrations. He also served as the CTO and Vice President of R&D at Voltaire, a high-performance computing, IO and networking company which floated on the NYSE in 2007 and was later acquired by Mellanox (NASDAQ:MLNX).

Yaron is an active contributor to the CNCF Working Group and was one of the foundation’s first members. He sits on the Data Science Committee of the AI Infrastructure Alliance (AIIA), of which Iguazio is a founding member. He is co-authoring a book on Implementing MLOps in the Enterprise for O’Reilly. Yaron presents at major industry events worldwide and writes tech content for leading publications including TheNewStack, Hackernoon, DZone,Towards Data Science and more.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google