Managing risks in Gen AI + Software engineering best practices in ML projects

Please join us for a fantastic PyLadies London meetup in collaboration with QuantumBlack, AI by McKinsey!

Agenda:
6.30pm - Doors open, socialising, food and drinks offered by our sponsor
7.00pm - Talk 1: Managing Risks in Generative AI: Implementing Guardrails for Trustworthy Content - Elena Khaustova (Sr. ML Engineer @ QuantumBlack)
7.30pm - Talk 2: Embedding Software Engineering Best Practices into Machine Learning Projects with Kedro - Merel Theisen (Principal Software Engineer @ QuantumBlack)
8.00pm - Socialising
8.30pm - Finish

Talks

Title: Managing Risks in Generative AI: Implementing Guardrails for Trustworthy Content
Abstract: This talk will focus on the risks associated with Generative AI and underscore the necessity of establishing robust guardrails to ensure that the content it produces is trustworthy and compliant with regulatory standards. The session introduces an automated system for implementing these guardrails and provides a detailed explanation of its functionality and significance. We will also look at how this system can be applied to different AI use cases, with real examples showing how it improves content quality. This session is designed for all data professionals, regardless of their technical background, and aims to provide practical insights into making Generative AI safer and more reliable.

Title: Embedding Software Engineering Best Practices into Machine Learning Projects with Kedro
Abstract: In this talk, I will explore how software engineering best practices such as modularity, separation of concerns, testability, and reproducibility can elevate the quality and deployability of machine learning projects. Focusing on the Kedro framework, I’ll uncover how these principles integrate into data workflows, making complex projects more manageable and scalable. Attendees will gain practical insights into improving project design, ensuring code quality, and facilitating smoother transitions to production environments. No extensive software engineering background is required, making this an accessible and informative session for all data professionals looking to enhance their knowledge of software principles through Kedro.

Sponsor: This meetup is sponsored by QuantumBlack, AI by McKinsey.