Exploring Open-Source Multi-Agent Frameworks for ML Research

Hosted by Amir Feizpour and Mykola Burynok

80 students

What you'll learn

Automating ML research workflows

Steps towards automating ML research workflows with open-source multi-agent architectures

Generating complex technical documents

Produce peer-review-ready documentation with minimal human input

Orchestrating multiple agents from different frameworks

Tackle the integration of building blocks from diverse multi-agent frameworks

Why this topic matters

We explore how open-source multi-agent frameworks can support ML research workflows by automating key stages, from data processing to model development and reporting. We'll showcase task-specific agents designed for planning, development, and validation phases, each contributing to peer-review-ready documentation with minimal human input, and importantly will talk about the integration challenges.

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. 

Mykola Burynok

Senior Software Engineer @ Kima Inc.

Mykola is a seasoned software engineer and product builder with over 15 years of experience developing mobile apps, developer productivity command-line tools, and full-stack product architectures. Mykola has worked across startups and established companies, always focused on creating tools that are not only functional but intuitive and scalable. These days, Mykola helps turn recruitment and employee experience journey workflows into practical tools—faster and smarter. Fascinated by the intersection of engineering and anthropology, Mykola is now diving deep into agentic architectures and AI-powered productivity systems, exploring how intelligent collaboration between humans and machines can shape the future of work.

© 2025 Maven Learning, Inc.