Inside BMW's AI Gateway: Self-Hosting Cost-Efficient AI at Enterprise Scale | BMW | Ray Summit 2026
Relying on APIs is a straightforward Day 1 solution, but the reality of production AI is that long-term enterprise scale requires self-hosting. At Ray Summit 2026, Thomas Riedl, AI Platform Engineer at BMW Group, goes inside BMW's AI Gateway, the core of the Connected AI Platform bridging global engineering teams, a vast array of models, and millions of connected vehicles. He unpacks how BMW manages high-volume production traffic and maximizes hardware efficiency, showcasing the specific Ray and vLLM strategies that slash inference costs and power real-world applications at scale. You'll leave with the architecture and economics of the transition to self-hosted AI at enterprise scale. Liked this video? Check out other Ray Summit breakout session recordings: https://www.youtube.com/playlist?list=PLZNaJyYZRPdo Subscribe to our YouTube channel to stay up-to-date on the future of AI: https://www.youtube.com/c/anyscale š Connect with us: LinkedIn: https://www.linkedin.com/company/joinanyscale/ X: https://x.com/anyscalecompute Website: https://www.anyscale.com/