LinkedIn x SGLang: Discover the Future of LLMs for Search and Recommendation

​🚀 LinkedIn x SGLang: Discover the Future of LLMs for Search and Recommendation

​Join us for an evening of deep technical insights into how large-scale LLM systems are built, optimized, and deployed in real-world production environments.

​This meetup brings together engineers/leaders from LinkedIn, SGLang, TikTok, Meta, SNAP, NVIDIA and more to share practical lessons from running inference at scale — covering modeling optimizations, distributed serving, ranking systems, semantic search, and open-source collaboration.

​If you care about:

• ​⚡ High-performance inference

• ​🧠 LLM-based ranking & search

• ​🔬 Modeling + systems co-optimization

• ​🌐 Open-source infra at production scale

​This event is for you.

​📍 In-Person Event (Mountain View)

​This is an in-person event hosted at LinkedIn’s Mountain View campus.

​Please register only if you’re able to attend in person, as capacity is limited and we expect a full room.

🗓 Agenda

​ 5:00 PM – Doors Open & Networking
5:30 PM – Welcome
5:40 PM – LinkedIn LLM Recsys Deep Dive
6:30 PM – SGLang Roadmap & RL Framework Keynote
7:10 PM – Break
7:20 PM – Industry Talks (TikTok, Meta, NVIDIA)
8:15 PM – Guest Panel & Open Q&A
9:00 PM – Networking & Socializing

​🎤 Featured Talks

​🔵 LinkedIn Production Deep Dive

​ Engineering talks on LLM RecSys at LinkedIn:

• ​Semantic Search at scale

• ​Modeling optimizations for ranking

• ​LLM inference infrastructure optimizations

​🟣 SGLang Roadmap & RL Framework

• ​H1 Roadmap and future direction

• ​Reinforcement Learning framework updates

​🟡 Industry Talks

• ​TikTok LLM Recsys Talk

• ​Meta Generative Reasoning Reranker

• ​NVIDIA