AI Security London
Hey everyone,
Join us for our next AI Security meetup on March 26th, once again at the Snyk offices in central London, featuring 2 new talks.
And as always, there’ll be drinks, pizzas, and a great crowd — so expect a fun evening as well.
Don't forget to RSVP now!
Talk 1 - Securing AI with AI: Building a Security Gate for Production Agents
In production, any input could be malicious. This talk covers how my team built a security validation layer for an AI agent at Snyk. I’ll walk through the attack categories we defend against (prompt injection, system manipulation, data exfiltration, role-play bypasses), and the unexpected challenges that come with securing an agent that's purpose-built for security workflows.
Speaker: Jada Ross - AI Systems Engineer at Snyk. Jada is an AI Systems Engineer at Snyk, building production AI systems that help teams move faster and smarter. She's shipped RAG pipelines, LangGraph agents, and knowledge systems, embedded her work across engineering, go-to-market, support, and strategy teams at Snyk.
Talk 2 - From Bias to Trust: A Day in the Life of a Responsible AI Product
Building "Responsible AI" is often seen as a compliance hurdle, but for a business to scale, it must be the foundation of the architecture. In this session, we follow the end-to-end journey of a single AI use case—from the boardroom to the server room. We will explore how different roles—Business Owners, Data Scientists, Architects, and Delivery Leads—can identify and mitigate ethical risks at every stage of the lifecycle. You’ll walk away with a practical "Day 1" checklist to ensure your AI is not just powerful, but trustworthy.
Speaker: Gayatri Pandey is a Strategic Product Manager with over 13 years of experience in the technology sector. She specializes in bridging the gap between deep technical engineering and high-level business strategy. Gayatri’s expertise is backed by the AI for Business Leaders program at MIT, the Artificial Intelligence program at Oxford, and a 12-week intensive Applied Data Science bootcamp. With a foundational background as a Data Engineer—where she personally deployed ML models to servers—she brings a unique, "full-stack" perspective to the challenges of scaling responsible and ethical AI systems.