About us
Join the Minneapolis AI Engineer Meetup, where builders and creators come together to turn AI possibilities into shipped realities. Whether you're a seasoned ML engineer, full-stack developer exploring AI integration, or a technical leader, you'll find your people here—fellow practitioners who transform AI research into products people actually use. As the Minneapolis chapter of the global AI Engineer community (https://www.ai.engineer/), we dive deep into sharing war stories, debugging challenges together, and learning cutting-edge tools that actually work in production.
Come ready to discover actionable techniques that drive results, build relationships with other engineers navigating the AI landscape, and celebrate the products that make it from concept to deployment. Come for the technical insights, stay for the community of makers who get it and are building the future, one deployment at a time.
Join the #minneapolis channel on the AI Engineer / Latent Space Discord server (https://discord.gg/xJJMRaWCRt) to stay in touch between meetings.
Upcoming events
1
AI Engineering Meetup: Serve It Fast. Understand It.
Industrious — T3 Building, 323 N Washington Ave, Suite 200, Minneapolis, MN, USHeads up: new start time. We now start at 4:30 PM, a half hour later than before, so we fit better with Industrious's schedule. If you show up at 4:00 out of habit, you'll be early.
This month, Sona Maniyan takes us inside vLLM and the memory trick that makes serving LLMs fast. Then we'll watch Geoffrey Litt's AIE World's Fair talk on how to keep understanding code when your agents are writing most of it.
Sona Maniyan: vLLM: LLM Serving with PagedAttention.
Serving large language models at production scale is a different problem than training them. A big reason is the KV cache, which grows with every request and leads to fragmentation and over-allocation in traditional inference engines. PagedAttention borrows virtual memory paging from operating systems and stores KV cache blocks noncontiguously. Sona walks through how that works, then digs into vLLM, the open-source inference and serving engine built around it: a practical walkthrough, performance benchmarks (up to 24x higher throughput in the right comparisons), who's using it, and how you can contribute.Video from AIE World's Fair · Geoffrey Litt: Understanding Is the New Bottleneck
Agents now write pull requests faster than anyone can read them line by line. Geoffrey Litt, a design engineer at Notion, argues the scarce resource isn't writing code anymore. It's understanding it. He walks through three ways to keep humans in the loop: agent-written explanations, interactive playgrounds that build intuition, and shared spaces where people and agents work from the same context. We'll watch it together and talk about it after.
Grab a snack, grab a seat, and bring your questions.Agenda
Wednesday, November 11
🥨 4:30 PM · Doors open + snacks and networking
👋 5:00 PM · Welcome and intro remarks
🎤 5:10 PM · Sona Maniyan presents: vLLM: LLM Serving with PagedAttention
📺 5:40 PM · Video: Geoffrey Litt, Understanding Is the New Bottleneck
💬 6:10 PM · Networking and discussion
🚗 6:30 PM · Go home and buildAddress
Industrious, T3 Building
323 N Washington Ave, Suite 200 (2nd floor)
Minneapolis, MN 55401Parking
Street parking is available, including metered spots in front of the building (2-hour limit). You can also park in Ramp C. From Ramp C, exit on the basement level on the northeast side (3rd Ave exit), walk around to the front of the T3 building, and come in the main doors.Food + Drink
Food provided at 4:30 PM courtesy of our sponsor, Blank Metal. Drinks and the space courtesy of Industrious.What to Bring
Just yourself. We've got everything covered.Important to Know
Registration is free but required. Please RSVP so we can plan for capacity.Accessibility
The T3 building is wheelchair accessible, with ramped curb access to the main entrance on N Washington Ave and an elevator to the 2nd floor.20 attendees
Past events
12
