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

Elena has migrated four companies from notebooks to production and has strong opinions about which parts of that journey are optional.

• From Notebook to Nine-Nines: Productionising ML
• Human-in-the-Loop Without Being Human-Hostile

Grace designs and ships AI features end to end, and has opinions about streaming interfaces that she will share at length.

• Human-in-the-Loop Without Being Human-Hostile

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.

• The Economics of Context Windows
• Sponsor Showcase: Kestrel Compute
• Cutting Inference Costs 70% Without Touching the Model

Kwame works on inference runtimes and open-model deployment on hardware that was never meant for it.

• Prompt Caching, Batching and Other Boring Wins

Marcus Okafor is a Staff Developer Advocate at Cloudreach Labs focused on AI agents in production. He writes the newsletter 'Agents Weekly' and co-organizes the SF AI Tinkerers meetup.

• Lightning: Agents in Production Q&A
• UPDATED: Taming 40-Minute CI: Incremental Builds at Monorepo Scale

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 Raman is a Principal Engineer at Latticework Systems where she leads the build-tooling platform team. She previously maintained the open-source task runner 'gantry' and has spoken at over a dozen developer conferences on build systems, CI reliability, and developer productivity metrics. SBEK-PORTAL-BIO-01

• Your AI Pair Programmer Is Lying to You: Verification Patterns That Scale
• Docs That Answer Back: Retrieval-Grounded Documentation Sites
• UPDATED: Taming 40-Minute CI: Incremental Builds at Monorepo Scale

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.

Sofia manages two platform teams and treats developer experience as a reliability concern.

• Human-in-the-Loop Without Being Human-Hostile

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