Building AI Systems: Architecture, Team, and Trade-offs

Hosted by Amir Feizpour and Ian Yu

Fri, Sep 12, 2025

4:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Build Multi-Agent Applications - A Bootcamp - LangGraph, Cursor, n8n
Amir Feizpour, PhD
View syllabus

What you'll learn

how team structure shapes AI system design.

how maintenance needs affect architectural choices.

how to build AI services with future flexibility in mind.

Why this topic matters

After deploying different flavours of AI orchestration frameworks and RAG systems, Ian shares observations on making sustainable technology choices. This talk examines how team structure, maintenance requirements, and future flexibility should inform architectural decisions around abstraction and coupling in AI services.

You'll learn from

Amir Feizpour

Founder @ Aggregate Intellect

Amir Feizpour is the founder, CEO, and Chief Scientist at Aggregate Intellect building a generative business brain for service and science based companies. Amir has built and grown a global community of 5000+ AI practitioners and researchers gathered around topics in AI research, engineering, product development, and responsibility. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir also serves the AI ecosystem as an advisor at MaRS Discovery District, works with several startups as fractional chief AI officer, and engages with a wide range of community audiences (business executives to hands-on developers) through training and educational programs. Amir leads Aggregate Intellect’s R&D via several academic collaborations.

Ian Yu

MLE @ Rezolve AI

Ian Yu works as Machine Learning Engineer at Rezolve AI while serves as independent consultant for startups. He has designed and deployed Generative AI projects and high-fidelity RAG solutions in different flavours, from small team to solutions requiring high QPS at sub-second latency. His projects cover eCommerce, automobile, and legal domains.

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.