Speaker wall

Amara builds retrieval systems that survive contact with real users. She has spent eight years on search infrastructure and now leads the applied AI group at Northwind Labs.

• The RAG Is Dead, Long Live Retrieval

Diego works on evaluation tooling and spends most of his week arguing that a benchmark you cannot reproduce is a rumour.

• Evals as a Product Surface: Making Quality Legible

Jonas has been on call for GPU fleets since before it was fashionable. He writes about scheduling, spot capacity and the true cost of a token.

• Sponsor Showcase: Kestrel Compute
• Cutting Inference Costs 70% Without Touching the Model

Mei-Lin is a founding engineer at Tessellate, building structured-output tooling for teams who need model responses to be parseable on the first try.

• Structured Output Is a Distributed Systems Problem

Priya runs the platform team at Lumen Systems, where she is responsible for the inference tier that everything else quietly depends on.

• Cutting Inference Costs 70% Without Touching the Model

Samuel leads engineering at Pathfinder Robotics, where models plan and humans still hold the stop button.

• Shipping Agents That Don't Melt Down at 3 A.M.

Tobias maintains three open-source agent libraries and one very long changelog. He cares about docs more than demos.

• Building a Tool-Calling Runtime in 300 Lines

Yuki bridges research and product, mostly by writing the harness nobody else wants to write.

• Observability for Nondeterministic Systems