AI Security Engineers - London, UK

Join us for a joint meetup with our friends from Qodo and Tessl

AI coding agents are increasingly embedded in production workflows, but their failure modes are often poorly understood, difficult to detect, and even harder to evaluate systematically.

​This session examines how agent-based systems degrade under real-world conditions, focusing on three critical dimensions: reliability, code quality, and security. We’ll look at where current evaluation approaches fall short, how non-determinism and context drift impact correctness, and why seemingly “successful” generations can still introduce latent defects or vulnerabilities.
​If you’re building, evaluating, or deploying AI agents in production systems, this session will provide a grounded view of where they fail and what it takes to make them robust

Agenda

• ​​​6:00pm Venue opens
• ​Join us for Drinks and Pizza!
• ​​​6:30pm Hidden Failure Modes for AI Agents by Nupur Sharma
• ​6:50pm Panel Discussion
• ​Panelists
• ​Simon Maple - Developer Relations at Tessl
• ​Brian Vermeer - Staff Developer Advocate at Snyk
• ​Nupur Sharma - Solutions Engineer at Qodo
• ​Kunal Kushwaha - Senior Developer Advocate EMEA at Cast AI

SPEAKERS
​
Simon Maple - Developer Relations at Tessl
​Simon Maple is the Head of Developer Relations at Tessl, and AI Native Dev co-host. Previously, Simon was the Field CTO, and VP Developer Relations at Snyk, ZeroTurnaround, and IBM. He became a Java Champion in 2014, JavaOne Rockstar speaker in 2014 and 2017, Duke’s Choice award winner, Virtual JUG founder and organiser, and London Java Community co-leader
​
​Brian Vermeer - Staff Developer Advocate at Snyk
​Staff Developer Advocate for Snyk, Java Champion, and Software Engineer with over a decade of hands-on experience in creating and maintaining software. He is passionate about Java, (Pure) Functional Programming and Cybersecurity. Brian is a JUG leader for the Virtual JUG and the NLJUG. He also co-leads the DevSecCon community and is a community manager for Foojay. He is a regular international speaker on mostly Java-related conferences like JavaOne, Devnexus, Devoxx, Jfokus, JavaZone and many more. Besides all that, Brian is a military reserve for the Royal Netherlands Air Force and a Taekwondo Master / Teacher.
​

​Nupur Sharma - Solutions Engineer at Qodo
​

​Kunal Kushwaha - Senior Developer Advocate EMEA at Cast AI

***

AI Security Summit London — May 14, 2026

Hey everyone, we're partnering with the upcoming AI Security Summit in London. You can already register to attend the Practitioner Track:

This isn’t high-level fluff. This is about working with real AI systems — understanding how they break, and how to secure them properly.
Expect live model exploitation demos, architecture teardowns from teams shipping AI at scale, and hands-on workshops where you’ll actively break systems — then fix them.
From LLM security to AI red teaming and secure-by-default development, everything is grounded in real-world practice from people doing this work every day.

🎤 Call for Speakers (CFP) is open
Got a live demo, workshop, or architecture teardown to share? We’d love to hear from you. 👉 Apply now: https://sessionize.com/ai-security-summit-london

📍 Venue & Schedule

• CodeNode London
• 🕘 9:45 AM – 4:30 PM
• 🍻 Happy Hour until 7:00 PM

👩‍💻 Who Should Attend
This track is designed for hands-on practitioners, including:

• Engineers building AI features and infrastructure
• Application Security (AppSec) teams testing those systems
• AI/ML engineers and researchers deploying and tuning models
• Platform and architecture engineers managing pipelines and endpoints
• AI security practitioners focused on detection and response

🧠 What You’ll Learn

• Threat modeling for AI/ML with real attack patterns and failure cases
• Securing models, training data, pipelines, and inference endpoints — with concrete configs and code references
• Live red team demos — including prompt injection, misuse chains, and model abuse scenarios
• LLM security hardening — prompt safety, hallucination controls, and abuse mitigation techniques
• Detection & monitoring playbooks — key logs, thresholds, and incident response strategies that work in production

Join us in London to connect with fellow builders and defenders — and leave with practical knowledge you can use right away.