
Seiji Eicher
Software engineer- Distributed LLM Inference
In-person · Las Vegas · April 22 - 24 2026
April 22, 2026 | 4:00PM - 4:25PM
Learn how to deploy the Qwen model on GKE with Ray Serve and vLLM for fast, scalable inference. Discover how to integrate an ADK agent for advanced chat and tool use, leverage TPU nodes, and use Ray’s autoscaling and fault tolerance to build enterprise-ready agentic AI systems.

Software engineer- Distributed LLM Inference

Senior AI Engineer
April 24, 2026 | 11:00AM - 11:45AM
Join this session to explore Mistral AI’s RL strategies and Anyscale’s high-performance Ray on Google Kubernetes Engine (GKE). We’ll analyze GKE primitives for faster RL loop times, focusing on sampling, weight transfer, and sandboxing for isolation.

Member of Technical Staff

Product Manager

Software Engineer
Visit Coreweave booth at #1815 at 2:00pm on April 22 to catch a live demo.
April 22, 2026 | 6:30PM - 8:30PM
Join Intel and Anyscale for an exclusive evening of networking over drinks and appetizers. Enjoy great food, curated cocktails, and a few surprises along the way. This invite-only experience has limited capacity—be sure to register in advance to secure your spot.
April 22, 2026 | 4:00PM - 6:30PM
The Innovation Exchange: Emerging Tech for Enterprise is an invite-only networking experience hosted during Google Cloud Next, designed to connect founders and executives with a select group of Intel Capital portfolio companies driving innovation across AI, security, and data.
(Please Indicate that you were invited by Anyscale)