| |
|
Multimodal Engg Night
|
| With Harish Wajjala (Principal ML Enggr, Roblox), John Kupchanko (Qdrant), Caroline di VIttorio (LangChain). |
|
Oct 22 (Thu) @ 05:30 PM
FREE
| | Venue, To Be Announced, SF
|
|
|
|
|
| |
| Register |
|
|
| |
Join us for an evening of engineering talks, live demos, & networking with Roblox, Qdrant, Superoptimal, The AI Collective, & Code & Coffee.
About The Event
Multimodal Engineering Night is a meetup for engineers working on AI beyond text: images, 3D scenes, game state, & real product signals. From vector search in gaming to understanding 3D worlds without rendering them, expect a night of speakers & community demos.
Space is limited to 70, & registration is approved by the hosts, so register early.
Event Agenda
5:30pm Doors open
6:10pm Roblox: Beating Video Games with Vector Search
6:25pm Qdrant: Multimodal Retrieval in Production
6:40pm LangChain: Voice Agent Evaluations
7:00pm Community demos
7:45pm Networking, food & drinks
9:00pm Close
Talk 1: Understanding 3D Worlds Without Rendering Them
Harish Wajjala | Principal Machine Learning Engineer, Roblox - LinkedIn
What if you could understand a 3D game scene without rendering it first? Harish will explore how asset & position data can support scene-level embeddings for questions & classification, sidestepping the render-then-image pipeline. Hell connect the approach to Roblox Economy use cases, including avatars & in-game transactions, & distinguish whats partly in production from whats still being explored.
Talk 2: Beating Video Games with Vector Search
John Kupchanko | Qdrant - LinkedIn
What happens when you point a vector database at a video game? This talk walks through building an agent that uses vector search to play & win: embedding screen frames & game state, retrieving the right memory at the right moment, & the engineering decisions that separate an agent that wanders from one that finishes the game.
Talk 3: LangChain Voice Agents Evaluations
Caroline di VIttorio | LangChain - LinkedIn
What makes a voice agent reliable beyond simply sounding human? This talk explores how to evaluate voice agents across three dimensions: execution, outcomes, & experience. Learn how to assess whether an agent follows instructions & uses tools correctly, achieves its intended goal, & delivers a smooth conversation without awkward pauses, interruptions, or frustrating delays. Discover how to use LangSmith for tracing & evaluating voice agents, identifying failures, & debugging behavior to build voice agents that are ready for production.
Community Demos
Built something multimodal, from a vision pipeline to a voice agent to a retrieval-based game? We have three 5-minute demo slots. Message the hosts on Luma with a one-line description of what youd show.
Who Should Join?
Whether youre working on computer vision, speech & audio, 3D & generative media, AI agents, search & relevance, embeddings, or vector databases, theres plenty here for you. In town for AGNTCon or MCPCon that week? This is the evening to meet the SF builders. Come for the engineering insights. Stay for the food, drinks, & people.
Space is limited to 70, & registration is approved by the hosts register early.
Who Are We
The AI Collective is a global non-profit building the human layer for the AI era. We unite 200,000+ leaders, builders, & stakeholders across 100+ forums worldwide to democratize the frontier, build trust, & coordinate how society navigates the rapid acceleration of technological progress.
Code & Coffee is a meetup for developers to make friends & grow, active in over 30 cities. 100% volunteer-led & volunteer-run, with 80,000+ devs & growing.
Superoptimal runs technical meetups & workshops for AI engineers, bringing practitioners together around real production systems.
Upriver is the API that gives AI agents real-time context on emerging trends & breakout topics, so teams act on whats timely & relevant for target audiences.
|
|
|
|
|
|
|
|
