Architecting the Future: An Evening of High-Stakes AI Engineering

Welcome to DSF Sandbox Sessions!

Top tech talks and masterclasses from the best in the industry. Every month, and completely free. The catch? There isn’t one. Just a monthly dose of epic content to power up your data passion!

⭐️ Event: Architecting the Future: An Evening of High-Stakes AI Engineering
📆 Date: Thursday 9th July 2026
⏰ Time: 6:00 – 9:00 PM BST
📍 Location: London, UK

🎟️ CLICK HERE TO ENTER THE BALLOT! 🎟️

💡 About the event:

The “Chatbot” era of AI is over. For technologists in Financial Services, the real challenge is not writing a prompt. It is orchestration, security at scale, and integrating AI into complex, business-critical systems.

Join Faculty and the Data Science Festival for our final in-person meetup before the summer break. This evening is designed specifically for practitioners building production AI systems and navigating the realities of deploying GenAI in regulated environments.

We are stripping away the hype and taking a practical look at the architectural challenges, lessons learned, and engineering decisions involved in moving AI from proof of concept to production. Through two technical talks and a panel discussion, we will explore how organisations are building secure, scalable, and reliable AI systems that can operate in the real world. We will explore topics include retrieval systems, LLM orchestration, and agentic AI in enterprise environments.

No fluff. No “AI will change the world” introductions. Just senior practitioners, technical discussions, real-world architecture challenges, and a few drinks to facilitate the “how did you actually solve that?” conversations.

Food, drinks, and networking with fellow practitioners will be available throughout the evening.

Who is this for?

This event is curated for Senior and Lead Machine Learning Engineers, Software Engineers, DevOps Engineers, Data Architects, and Applied Scientists.

While many examples come from Financial Services and Insurance, the architectural patterns and engineering lessons will be relevant to anyone building production AI systems at scale.

Talk 1: Scaling the Haystack: The engineering reality of processing thousands of sensitive documents for retrieval
Brandon Lim, Senior ML Engineer @ Faculty

Most document processing pipelines look straightforward until you throw thousands of real-world files at them. Inconsistent formats, sensitive data, access controls, and scale all expose the gaps that prototype pipelines paper over. This talk covers the full journey from raw document ingestion to production-ready AI search: including data storage strategies, embedding and indexing, retrieval architecture, and how to keep quality and compliance intact as your corpus grows.

Talk 2: Claims Without the Hallucinations: A masterclass in LLM orchestration and deterministic outputs in production-grade environments.
Prudence Leung, Senior Data Scientist @ Faculty

In high-stakes corporate workflows, production reliability is on the frontlines of preventing severe financial, legal or regulatory risk. It’s about architecture: validating outputs at every boundary and orchestrating multi-step pipelines so they’re resumable, observable, and safe to retry.
This talk covers practical layers of that architecture, such as using Pydantic to turn LLM outputs into hard pass/fail gates, and durable execution frameworks like DBOS and Temporal to make multi-step pipelines resumable and safe to retry. The goal throughout is keep deterministic logic deterministic, and contain the probabilistic parts.

Talk 3: Panel - The Autonomous Underwriter: How do you integrate GenAI agents into legacy insurance systems without breaking the business?
Chris Mullan, Head of Data and AI @ CFC Underwriting
Divish Rengasamy, Lead ML Engineer @ Faculty
Hanne Carlsson, Senior Data Scientist @ Faculty
Hosted by Michelle Conway, Lead ML & AI Engineer @ Lloyds Banking Group

Agentic AI promises to transform underwriting but legacy systems, regulatory constraints, and organizational complexity make the path from demo to production far harder than it appears. Beyond the software engineering, this is a massive change management and operational transformation. Drawing on real-world experience, this panel unpacks the friction of decoupling agents from brittle dependencies, managing risk acceptance, and building systems that improve over time without creating new operational risks.

🕧 Schedule:
6:00 PM – Doors open – networking with food and refreshments
6:45 PM – Intro
6:50 PM – Talk 1 (including Q&A)
7:10 PM – Talk 2 (including Q&A)
7:30 PM – Short comfort break
7:40 PM – Panel discussion
8:20 PM – Networking with refreshments
9:00 PM – Event close

🎟️ CLICK HERE TO ENTER THE BALLOT! 🎟️

🎟️ IMPORTANT: Due to high demand and limited space, tickets for this event will be allocated by a ballot. Applying does not guarantee entry. Successful applicants will be notified throughout June and early July. If you have not received confirmation by July 6th, this means your ballot ticket was not drawn this time.

🚨 PLEASE NOTE: Clicking 'attend' does not register you for the event. You will need to register for the event on the link provided below to receive a QR code ticket via email. If you do not have a QR code, you will not be able to attend the event.