This track brings together the team's shipping state‑of‑the‑art systems to unpack how modern AI moves from prototype to production. Across sessions, you’ll see how code-first copilots are built and evaluated (Anthropic), how enterprise research agents ground answers in proprietary knowledge (Glean), and how reinforcement learning optimizes large‑scale marketplaces and ads (Meta). We’ll dive into AI content generation and agent‑based simulation for creative and safety‑aware workflows (Pinterest + Veris AI), personalization with LLMs that balances latency, cost, and relevance (DoorDash), and the emerging Model Context Protocol for interoperable tooling and orchestration (Browserbase).
Expect concrete patterns for retrieval and data pipelines, multi‑agent design, online/offline evals, guardrails and governance, observability, and continuous improvement loops, so technical leaders can deliver scalable systems that are reliable, compliant, and measurably impactful.
From this track
Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash
Tuesday Nov 18 / 10:35AM PST
In this talk, we’ll walk through how DoorDash is redefining personalization by tightly integrating cutting-edge large language models (LLMs) with deep learning architectures such as Two-Tower Embeddings (TTE) and Multi-Task Multi-Label (MTML) models.
Sudeep Das
Head of Machine Learning and Artificial Intelligence, New Business Verticals @DoorDash, Previously Machine Learning Lead @Netflix, 15+ Years in Machine Learning
Pradeep Muthukrishnan
Head of Growth for New Business Verticals @DoorDash, Previously Founder & CEO @TrustedFor, 15+ Years in Machine Learning
Deep Research for Enterprise: Unlocking Actionable Intelligence from Complex Enterprise Data with Agentic AI
Tuesday Nov 18 / 11:45AM PST
Deep Research as a consumer product redefined the AI space delivering true impact to many by searching through hundreds of websites, deeply thinking through the content, and generating a comprehensive report.
Vinaya Polamreddi
Staff ML Engineer; Agentic AI @Glean; Previously @Apple, @Meta, and @Stanford
Engineering at AI Speed: Lessons from the First Agentically Accelerated Software Project
Tuesday Nov 18 / 01:35PM PST
Claude Code is the first developer tool built specifically to maximize AI development velocity.
Adam Wolff
Engineer and Individual Contributor to Claude Code @Anthropic, Previously @Robinhood, @Facebook
Automating the Web With MCP: Infra That Doesn’t Break
Tuesday Nov 18 / 02:45PM PST
AI agents are only as strong as the infrastructure beneath them. In this talk, we’ll walk through the architecture behind Browserbase’s model context protocol (MCP), built to support stateful browser automation at scale.
Paul Klein
Founder @Browserbase, previously Director of Self-Service & Engineering Manager @Mux, Co-Founder & CTO @Stream Club, Technical Lead @Twilio Inc.
From Content to Agents: Scaling LLM Post-Training Through Real-World Applications and Simulation
Tuesday Nov 18 / 03:55PM PST
This talk presents a comprehensive journey through modern AI post-training techniques, from Pinterest's production-scale content discovery systems to enterprise agent training through Veris AI’s simulation.
Faye Zhang
Staff Software Engineer @Pinterest, Tech Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Large Distributed System
Andi Partovi
Co-Founder @Veris AI, Making AI Agents World-Ready
Improving Meta Generative Ad Text using Reinforcement Learning
Tuesday Nov 18 / 05:05PM PST
Reinforcement Learning with Performance Feedback (RLPF) unlocks a new way of turning generic GenAI models into customized models fine-tuned for specific tasks. This approach is especially powerful when combined with in-house data and performance metrics.
Alex Nikulkov
Research Scientist (RL lead for Monetization GenAI) @Meta
