Join us for a power-packed night of learning, sharing, and networking at AI Dev Day - Toronto. We are excited to bring the AI developer community together to learn and discuss the latest trends, practical experiences, and best practices in the field of AI, LLMs, generative AI, and machine learning.

In addition to the tech talks, there will be plenty of opportunities to network with AI developers, live demos by AI startups, panel discussion, and career opportunities.

Agenda (EDT):
- 4:30pm~5:30pm: Checkin, food/drink and networking
- 5:30pm~7:30pm: Tech talks, and panel
- 7:30pm: open discussion, mixer

Tech Talk 1: Working with LLMs at Scale
Speaker: Yujian Tang, Developer @Zilliz
Abstract: we’ll introduce LLMs and two main problems they face when it comes to production: high cost and lack of domain knowledge. We then introduce vector databases as a solution to this problem. We cover how a vector database can facilitate data injection and caching through the use of vector embeddings.

Tech Talk 2: Build a Streaming AI Agent using OpenAI, Vercel, and Astra DB
Speaker: Chris Bartholomew, Head of Streaming Engineering @DataStax
Abstract: Building prototypes with Generative AI is easy, building real applications ready for production is hard. Generative AI often needs large data sets both public and private for context, that is where vector databases come in. In this talk you will learn how to build a streaming AI agent using DataStax LangStream for rapidly building production-ready AI applications that harness the latest LLM and vector database technology. You will see a demonstration of a Q&A chatbot over private data from text-oriented data sources like PDF and HTML.

Tech Talk 3: Iterative Improvements from Feedback for LMs
Speaker: Yuxi Li, Founder @RL4RealLife
Abstract: Language models (LMs) like ChatGPT are phenomenal, yet, with issues like hallucinations and a lack of planning and controllability. AI aims for optimality. LMs are approximations, so we aim to bridge the LM-to-real gap. Grounding, agency and interaction are the cornerstone for sound and solid LMs. AI should adapt to humans, but not vice versa. Iterative updates are too expensive for monolithic large LMs, thus modular, smaller LMs are desirable. Reinforcement learning is a promising framework, for pre-training, fine-tuning, human alignment, prompting and augmenting with tools and APIs.

Lightning Talk 1: Build Safer AI with AI Compliance Agent
Speaker: David Van Bruwaene, co-founder and CEO @Fairly AI
Abstract: We will discuss how to interact effectively with generative AI models, while ensuring human-understandable controls remain in place.

Stay tuned as we are updating speakers and schedules.
If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Venue:
OneEleven, 325 Front St W 4th Floor, Toronto, ON M5V 2Y1, Canada Google Map

Lucky draw
We will raffle winners for prizes during the event. To enter the lucky draw, "comment" the post on LinkedIn: LinkedIn Post

Sponsors:


We are actively seeking sponsors to support our AI developers community. Sponsors will receive speaking opportunities, sponsor recognition, and post-event emails to our vast membership base of 10k+ in Toronto or 250K+ developers in global. Contact us for details.

Community on Slack
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #toronto channel)

Community Partners:
Contact us if you are interested in partnership.