All Road events
Stop 12 Sydney

Road to AI Engineer Sydney

AI Engineer Night

The last Sydney Night before the conference itself — one final round of talks and demos before we all head into December. Food and drinks on us — the last shout before the big one.

When
Wednesday, November 186:00 – 9:00pm
Where
Blackwattle Bar & BrewerySydney
Cost
FreeFully catered

Places are limited. RSVP now and we’ll send you the final details and any updates.

Confirmed speakers

On the night

Rupert Manfredi

Rupert Manfredi

Head of Design
Telepath

It's time for a new kind of software

Applications package a predetermined interface, data model and set of capabilities around somebody else’s idea of a task. Generative models can now produce software on demand, but generative UI today either sits atop the existing application stack or replaces the richness of the app with an interface disconnected from the data and capabilities needed to do useful work.

This talk asks what happens when we replace the app all the way down.

In this live, demo-led talk, I’ll use Television—a system we are building for full-stack generative software—to make the architecture concrete. I’ll walk through the post-app stack, the problems each layer solves, the alternatives we tried and why we arrived at the current design. The result is not an app with AI in it, or a chat box that launches apps, but software that can take a different shape each time while remaining connected to dependable state and real-world actions. I’ll cover the central trade-offs between generated and durable software, flexibility and consistency, and agent autonomy and legible control. Attendees will leave with a practical architectural model for building agentic software beyond the app for production systems—and an understanding of why generating pixels is the easy part.

Tanya Dixit

Tanya Dixit

Forward Deployed Engineer
Google

The Elephant and the Goldfish: Architecture Patterns for Cutting 70% of Agent Token Costs in Production

LLM providers sell you a 2-million-token context window like an elephant that never forgets. If you actually build production agents that way, your latency explodes, your retrieval drifts, and your CFO will shut you down in 90 days. In production, the best agents think like elephants, but operate like goldfish.

While frontier models offer million-token context windows, treating autonomous agents like an elephant that carries entire conversational histories and raw tool outputs into every turn leads to compounding inference costs, bloated time-to-first-token and severe retrieval distraction. Tanya introduces the Elephant and Goldfish architecture—an open engineering pattern that separates persistent system state from lean, task-scoped inference context.

Grounded in reproducible benchmarks across multi-turn agent tasks, the talk explores subagent boundary isolation, upstream semantic context pruning, multimodal triage and lightweight evaluation models. Attendees will leave with concrete patterns for auditing token leakage, benchmarking context compression and cutting agent operating costs without degrading task success rates.

Inga Pflaumer

Inga Pflaumer

Consulting CTO

Management Is Dead, Leadership Is Not

Engineering teams are getting smaller. A team of four with strong AI tooling now ships what took twelve people two years ago, and the org chart has not caught up. The first layer to feel it is middle management—the coordination tier that existed largely to move information between people who were too numerous to talk to each other directly. When the team fits in one room, that layer is overhead.

The conclusion many organisations draw is that leadership itself is what got automated away. That is the wrong read. Smaller teams make more consequential decisions per person, move faster than any review process can keep up with, and have fewer places to hide a bad call. What they need is not someone tracking status. They need direction, judgement about what not to build, and someone accountable for the quality of what the agents produce.

Drawing on her experience leading engineering teams through this shift, Inga will cover what genuinely disappears when teams shrink, what quietly becomes more important, and how to tell the difference before restructuring around the wrong one.

Short talks, live demos and candid engineering conversation

What to expect

AI Engineer Nights are for people turning AI ideas into working systems. Expect practical talks and demos from engineers building with models, agents, tools and infrastructure right now—not polished product pitches.

We leave plenty of room around the formal program to compare notes, meet collaborators and talk through the problems that rarely make it onto a slide.

  • Practical talks and demos from working AI engineers
  • Useful conversations with people facing the same production challenges
  • Dinner, drinks and time to meet the local community
RSVP