AI Engineers Tech Talk: August
Join us for the August edition of the San Francisco AI Engineers Tech Talk, a gathering focused exclusively on AI engineering. Whether you’re a seasoned machine learning engineer or a fullstack dev curious about how to work with LLMs, this is your space to dive deep into real-world projects, technical challenges, and creative solutions.
What to Expect:
We invite AI engineers to share something they’ve built, the challenges they faced, and how they solved them. It’s all substance, no fluff, designed for engineers by engineers.
This Month’s Presenters:
Adam Malone, Senior Director @ PromptQL
Building a Company Brain for AI Agents
PromptQL will share a self-organizing, Wikipedia-style knowledge layer that helps agents understand evolving organizational knowledge instead of relying solely on vector databases. The talk will explore intelligent retrieval, AI-assisted knowledge updates, and practical ways to reduce ambiguity and stale context, giving AI agents durable, evolving domain knowledge without fine-tuning or massive context windows.
Building your company ontology for context aware agent systems
AI agents are more effective when they can build on past knowledge instead of starting from scratch. Parcle will share how they're creating a shared memory layer that works across tools like ChatGPT, Claude, Hermes, and OpenClaw, giving AI agents persistent context and a better understanding of your work. The talk will explore cross-agent memory, shared context, and practical approaches to building more capable and consistent AI systems.
Luke Zhan, Software Engineer @ Altara
Defeating "Infinite Churn": A Plug-and-Play Architecture for AI Startups
AI startups must constantly balance shipping new features, meeting customer needs, and keeping up with rapidly evolving technologies. Altara will share how they're building a plug-and-play architecture that decouples product logic from infrastructure, making it easy to adopt new AI tools and cloud providers without rewriting the platform. The talk will explore modular system design, abstractions, adapters, and practical strategies for building scalable, future-proof AI products.
The Crowd:
You’ll be joining a mix of software developers, data scientists, AI engineers, and technical founders working at or curious about the future of applying AI at the application layer. It’s a casual, high-signal environment perfect for learning something new and meeting peers in the SF AI Engineering scene.
Agenda:
6:00 to 6:45 PM – Networking with pizza, beer, & wine courtesy of Fonzi AI
6:45 to 6:50 PM – Opening remarks
6:50 to 7:35 PM – Three 10 minutes Tech Talks with 5 minute Q&A
7:35 to 8:00 PM – Meet the speakers and connect with other attendees
About the host:
Fonzi is a recruiting platform focused exclusively on product and AI engineering hires in NYC and SF. We work with 75+ open roles across the best startups in the city.
Hiring?
Want intros to startups?