About
Passion for building/advising high impact companies and driving disruptions that…
Activity
13K followers
-
Brian Stevens shared thisOpen source is the foundation for compute from cloud to edge, and at Red Hat we have been leading the charge to make that true for production inference at scale as well. To understand the economic benefits, we commissioned Forrester Consulting to analyze the numbers, and our new TEI study shows a 233% ROI with Red Hat AI. Read the full study to see how standardizing your platform layer can drive real value: https://red.ht/4up4kdK
-
Brian Stevens reposted thisIt was a great pleasure to host CNBC at our Red Hat AI booth during the India AI Impact Summit this week in Delhi, and to share what we have been building together with customers, partners and the open source community. The momentum has been building as we continue to deliver a high performance AI platform that promises to deliver any model, using any accelerator, and running on any cloud. Daniel Aw Fytos Charalambides Navtez Bal Paul Whittard Garry Gray Philip Yeap Abhishek Shukla Mukesh Mehta Ausim Khan Mangesh Surve Misha Joshi Arpita Sengupta Ravi Goyal Joel Jackson Joe Fernandes Brian Stevens Vincent Caldeira James Lovegrove Tushar Katarki Jeff DeMoss Erwan Granger Karl Eklund Jeff Winn Vijay Chebolu Prasad Mukhedkar Tarun Ghai Kiran Challapalli abhishek vijra Elisa NavarroBrian Stevens reposted thisTHREE LEADERS. ONE BOOTH. THE REAL TALK ON AI IN INDIA. From the Red Hat booth at Bharat Mandapam during the India AI Impact Summit 2026, CNBC-TV18's Global AI Lens brings you insights from the team powering enterprise AI across India and Asia-Pacific. Steve Shirkey, Director, APAC AI Platform Misha Joshi, Senior Director, Head of Services (India/South Asia) and Ausim Khan, Director, Partner Ecosystem (India & South Asia) share Red Hat's vision for AI in India. Platform. Services. Ecosystem. The full stack of AI transformation—decoded. Global AI Lens | India AI Impact Summit 2026 HCLTech Red Hat d-Matrix Sid Sheth Dr. Ravi Gupta Pradip Thaker #GlobalAILens #IndiaAI #AIImpactSummit #CNBCTV18 #RedHat #BharatMandapam #EnterpriseAI
-
Brian Stevens reposted thisBrian Stevens reposted thisI’m so happy to share with you that this weekend (November 1st) there will be a great vLLM meetup in Beijing! We (Red Hat) together with our partners and friends in the community, such as the Ant Group, AMD, ByteDance and MetaX, co-host this event and we invite the most seasoned people in the community such as Michael Goin - the lead vLLM maintainer to give us a general update and llm-d’s latest features, and many others to share insightful topics - quite a few around distributed inference solutions and different accelerator support ways. So if you happen to be in Beijing this weekend, welcome to join in person! You can either drop me a message or register through “vLLM community” WeChat account! The meetup also has live-streaming, we will provide the live-streaming link shortly so please stay tuned;) Brian Stevens Brent Holden Vincent Caldeira Michael Goin Saša Zelenović Grant Shipley Tushar Katarki Christopher Nuland Jeff Winn Steve Shirkey Li Ming Tsai Andreas Spanner Chris Butler Vinod Pathangay Ken Komazawa Lisa Li
-
Brian Stevens shared thisThe pace of advancements in AI is stunning, and innovations in open source are driving the industry’s emerging capabilities in inference platforms, agentic architectures, and data integration. While that alone is a reason to celebrate, it's hard to keep up and a day doesn’t go by where I’m not investing time to learn something new. At Red Hat we decided to turn that inside out, and share a day-of-learning with like-minded colleagues. We’ve curated a virtual event of 12 session across 4 tracks: Inference and Optimization – Optimal deployment with vLLM, LLM Compressor, and Speculators. Model Customization – Connecting models to enterprise data Agentic AI – Building open and flexible agents with MCP, LlamaStack, and more. Scaling Across Hybrid Cloud – Learn distributed inference and scaling strategies with OpenShift AI. Register here: https://lnkd.in/e_UZ5qAG, and happy learning! Red Hat AI Day of Learning: Your Path to Enterprise-Ready AI October 16, 2025 | 10:00 a.m. - 11:30 a.m ESTRed Hat AI Day of Learning: Your Path to Enterprise-Ready AIRed Hat AI Day of Learning: Your Path to Enterprise-Ready AI
-
Brian Stevens reposted thisBrian Stevens reposted thisRed Hat AI Day of Learning: Your Path to Enterprise-Ready AI October 16, 2025 | Starts at 10:00 a.m. EST | Virtual Choose your own AI learning journey with 12 breakout sessions across 4 tracks: 1️⃣ Increase Efficiency with Fast, Flexible, and Efficient Inferencing 2️⃣ Simplified and Consistent Experience for Connecting Models to Data 3️⃣ Accelerate Agentic AI Delivery and Stay at the Forefront of Innovation 4️⃣ Flexibility and Consistency When Scaling AI Across the Hybrid Cloud Developers, engineers, and technical practitioners can mix and match sessions to focus on the topics that matter most and leave with practical skills to apply right away. Register here: https://lnkd.in/eCSDvYVyRed Hat AI Day of Learning: Your Path to Enterprise-Ready AIRed Hat AI Day of Learning: Your Path to Enterprise-Ready AI
-
Brian Stevens shared thisEldar Kurtić is amazing. Proud to be on his team.Brian Stevens shared thisWhen a brilliant mind from Bosnia and Herzegovina leads innovation at a global powerhouse like Red Hat, it’s impossible not to take notice. We’re proud to introduce another strong addition to our Engineering Stage this September — Eldar Kurtić, whose work pushes the boundaries of AI efficiency and deployment. ↳ Eldar Kurtić is a Senior Researcher at Red Hat and Institute of Science and Technology Austria, specializing in efficient inference techniques for large language models (LLMs), with a particular focus on sparsity and quantization. His work centers on developing methods to accelerate inference within the vLLM engine, bridging cutting-edge research with practical deployment solutions. At Kiss the Future AI Summit, Eldar will lead a hands-on workshop titled: “Beginner-Friendly Introduction to LLM Quantization: From Zero to Hero” He will cover: ↳ What quantization is — and why it matters ↳ How quantization fits into the architecture of LLMs ↳ Today’s leading quantization techniques for deployment ↳ How to quantize your own models ↳ Accuracy trade-offs and tuning for optimal performance ↳ Real-world inference cost and performance implications Whether you’re an ML engineer, AI researcher, or just getting started, this is your gateway to mastering LLM quantization. 🎟️ Did you know you can get a ticket just for the Engineering Stage? Head to Entrio now and secure your spot! The End of Hype. The Start of Impact. | 25th and 26th September #KissTheFutureAISummit #KisstheFuture #AISummitSarajevo2025 #EldarKurtic #RedHat
-
Brian Stevens reposted thisMore than happy to be part of this story! Thank you Blum Institut for the invitation.Brian Stevens reposted thisWhen a brilliant mind from Bosnia and Herzegovina leads innovation at a global powerhouse like Red Hat, it’s impossible not to take notice. We’re proud to introduce another strong addition to our Engineering Stage this September — Eldar Kurtić, whose work pushes the boundaries of AI efficiency and deployment. ↳ Eldar Kurtić is a Senior Researcher at Red Hat and Institute of Science and Technology Austria, specializing in efficient inference techniques for large language models (LLMs), with a particular focus on sparsity and quantization. His work centers on developing methods to accelerate inference within the vLLM engine, bridging cutting-edge research with practical deployment solutions. At Kiss the Future AI Summit, Eldar will lead a hands-on workshop titled: “Beginner-Friendly Introduction to LLM Quantization: From Zero to Hero” He will cover: ↳ What quantization is — and why it matters ↳ How quantization fits into the architecture of LLMs ↳ Today’s leading quantization techniques for deployment ↳ How to quantize your own models ↳ Accuracy trade-offs and tuning for optimal performance ↳ Real-world inference cost and performance implications Whether you’re an ML engineer, AI researcher, or just getting started, this is your gateway to mastering LLM quantization. 🎟️ Did you know you can get a ticket just for the Engineering Stage? Head to Entrio now and secure your spot! The End of Hype. The Start of Impact. | 25th and 26th September #KissTheFutureAISummit #KisstheFuture #AISummitSarajevo2025 #EldarKurtic #RedHat
-
-
Brian Stevens shared thisPersonally or professionally, every conversation I have w/ Chris Wright is always fun. This one was no different where we dove into vLLM and all things AI+Inference. Cheers.Brian Stevens shared thisHow do we take AI from research labs to robust, scalable enterprise production? Red Hat CTO Chris Wright and Red Hat AI CTO Brian Stevens dive deep into production-quality inference, the role of open source projects like vLLM, and the journey to practical enterprise AI. They discuss parallels with Linux's early days and the community effort needed to build the future AI stack. A must-listen for tech leaders navigating AI: https://red.ht/43ZcQWo.
Brian Stevens commented on a post
4mo
Congrats, am sure you will rock it!
-
Brian Stevens liked thisLooking forward to catching up with everyone and returning to the Engineering Stage in Sarajevo this October! Thanks Blum Institut for the invitation!Brian Stevens liked thisBosnia and Herzegovina on stage, and we wouldn't have it any other way. Those of you who caught Eldar's session last year know exactly why we made sure to bring him back. Meet Eldar Kurtić, Principal Research Scientist at Red Hat and the Institute of Science and Technology Austria, working at the intersection of AI research and real-world deployment. Eldar's work centers on making large language models faster and leaner, through sparsity and quantization techniques that push the boundaries of what efficient inference actually looks like. He's actively developing methods to accelerate inference within the vLLM engine, which means his research doesn't just live in papers, it ships. This year, he's bringing a topic that's quickly become one of the hottest conversations in the field: Speculative Decoding. Whether you're just getting started or already deep in the weeds, Eldar's talk promises to take you from zero to hero. Join Eldar on Kiss the Future Engineering stage on October 15-16th in Sarajevo. Grab your tickets via Entrio: https://lnkd.in/ddTMUAf4 Eldar, welcome back to Kiss the Future. We're so glad to have you with us again. #KissTheFuture #KTF2026 #AISummit #SpeculativeDecoding #RedHat
-
Brian Stevens liked thisBrian Stevens liked thisI had the pleasure of participating in a few great sessions with my colleagues at the ScotiaTech town hall last week. It was such a pleasure to see everyone come together to celebrate our progress and highlight our plans for the future of this extremely capable team. As you can imagine, a big topic of conversation was around AI – which is especially timely given our launch this week of several new Scotia Intelligence capabilities. Along with my colleagues Joe Martinez and Neha Mudalgikar, we discussed how engineering excellence and a strong security mindset need to coexist for us to continue shaping the safe adoption of this transformative technology across the bank. I then joined Cathy K., Jonathan Echeverria and Sebastian Blandizzi for a very energetic discussion about what’s really driving this success: our people. The team has generated great momentum over the last six months, which can all be attributed to the passion and talent of the amazing team that are all a part of #ScotiaTech. A fantastic kick off to the summer! #ScotiaTech #Scotiapride
-
Brian Stevens liked thisBrian Stevens liked this🎉 llm-d v0.7 is officially live! If our earlier releases proved what llm-d could do, v0.7 is about making sure you can easily deploy and run it in production. Backed by a 3.5x surge in community PR volume, this release focuses entirely on production hardening, eliminating operational friction, and expanding hardware reach. Here is the quick technical breakdown of what’s new: ⚙️ Streamlined Day-1 Ops: Clone to serving in minutes using the new Standalone Mode (Envoy default), plus a complete migration to Kustomize-first deployment pipelines. 🔌 Blackwell & Multi-Hardware: Upgraded to CUDA 13 for native NVIDIA Blackwell support, alongside validated production images for AMD ROCm, Intel XPUs, Google TPUs, and Rebellions ATOM. 🧠 Workload-Aware Routing: Introduced experimental Flow Control to eliminate noisy-neighbor issues, and an OpenAI-compatible Batch Gateway for heavy offline workloads. 💾 Tiered KV Caching: Real-time prefix cache tracking is now enabled by default, paired with seamless cache offloading from GPU HBM to CPU and persistent storage (AWS EFS/NVMe). We’ve also added 10,000+ lines of brand-new documentation and an overhauled, multi-platform CI matrix to ensure what we guide is exactly what you deploy. A massive thank you to our 23 new contributors and hardware ecosystem partners for making this milestone happen. Read the full architectural breakdown on our blog: 👇 https://lnkd.in/eHvUECVQ #AIInfrastructure #LLMInference #OpenSource #Kubernetes #PlatformEngineeringllm-d v0.7: From Feature Introduction to Production Hardening | llm-dllm-d v0.7: From Feature Introduction to Production Hardening | llm-d
-
Brian Stevens liked thisAmazing timing to have the Red Hat global team in Ottawa for the launch of the Government of Canada AI for All strategy! Especially when the global SVP and Head of AI Brian Stevens was in town with Public Sector CTO, John Dvorak . A great opportunity to talk about automation, AI, sovereign datacentres, IP, open source and acceleration hubs! Corey Somers Jason Barton Juan Berlie Roch Cousineau Paul Pinkney Kenneth Canam Christian Roy Louise Girouard Melissa Cable-Cibula Marci Surkes Compass Rose
-
Brian Stevens liked thisBrian Stevens liked thisI recently co-authored a blog with Erwan Gallen and Chris Procter on using #rebellions NPU on Red Hat AI Enterprise based on our recent joint solution announcement. Together, Red Hat AI and Rebellions ATOM NPUs help advance an open AI ecosystem where customers can run the models they want on the accelerators that best fit their needs, while delivering strong performance and energy efficiency. Many thanks to the various teams for making this happen: 1. Red Hat AI leadership (Brian Stevens Joe Fernandes Tushar Katarki) 2. Red Hat AI Inferencing Engineering team (Taneem Ibrahim Selbi Nuryyeva Nicolò Lucchesi Daniele Trifirò Michael Goin) 3. Red Hat Ecosystem Engineering (Nenad Perić Pablo Iranzo Gómez Chris Procter) 4. Our Inference PM (Erwan Gallen) 5. Rebellions' team (Minwook Ahn jinmoo Seok) Link: https://lnkd.in/gXftR5Xy Steve Shirkey Steven Huels Daniel Aw Ameeta Roy Vincent Caldeira Itamar Heim Hong-Seok Kim #redhat #rebellions #vllm #inference #kubernetes #redhatai
-
Brian Stevens reacted on thisBrian Stevens reacted on thisKubernetes didn't win because it was the first container orchestrator. It won because it became the open standard everyone could build on. AI inference needs the same moment. LLM workloads are stateful, latency-sensitive, and wildly variable in cost. Standard service routing wasn't built for this. That gap is exactly what llm-d addresses. By contributing llm-d to the CNCF, Red Hat, alongside CoreWeave, IBM, Google, and NVIDIA, is making a long-term bet: that the future of enterprise AI runs on open standards, not proprietary lock-in. Read more: https://red.ht/4tK5n7d #OpenSource #CNCF #AIInference #CloudNative #RedHat #llmd #EnterpriseAI
-
Brian Stevens liked thisBrian Stevens liked thisWhere open-source innovation meets enterprise scale! Had a great time at Red Hat Summit 2026 in Atlanta. !AMD and Red Hat are advancing the next wave of AI and hybrid cloud—delivering performance, flexibility, and choice for customers. Energizing conversations across the ecosystem—and always a pleasure catching up with my good friend Brian Stevens!
-
Brian Stevens liked thisBrian Stevens liked thisBuilding a durable AI ecosystem through open innovation - SiliconANGLEBuilding a durable AI ecosystem through open innovation - SiliconANGLE
Experience & Education
-
Red Hat
View Brian’s full experience
See their title, tenure and more.
or
Other similar profiles
Explore more posts
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top contentOthers named Brian Stevens
841 others named Brian Stevens are on LinkedIn
See others named Brian Stevens