AI Engineer

Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog

GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod

RAG is dead, right?? — Kuba Rogut, Turbopuffer

From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind

Road to 5 Million Tokens: Breaking Barriers in Long Context Training — Max Ryabinin, Together AI

Why More Context Makes Your Agent Dumber and What to Do About It — Nupur Sharma, Qodo

Agentic systems in software development face significant hurdles, particularly regarding context management and the "orchestration paradox." LLMs often fail to process middle-context effectively, leading to unreliable results. To mitigate this, developers should move beyond simple context dumping toward structured solu...

Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare

LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize

Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod

From MCP to Scale: Pipelines That Build Themselves — Rafael Levi, Bright Data

Building Interactive UIs in VS Code with MCP Apps — Marlene Mhangami & Liam Hampton, GitHub

Evals Are Broken, Use Them Anyway — Ara Khan, Cline

Building safe Payment Infrastructure for the autonomous economy — Steve Kaliski, Stripe

Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents — Michael Hablich, Google

Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw

Beyond Transcription: Building Voice AI That Understands Conversations — Hervé Bredin, pyannoteAI

Text Diffusion — Brendan O’Donoghue, Google DeepMind

The Art & Science of Benchmarking Agents — Vincent Chen, Snorkel AI

SWE-rebench: Lessons from Evaluating Coding Agents — Ibragim Badertdinov, Nebius

AI Engineer Melbourne 2026 Keynote Livestream | Day 2