geekyroshan
Back to Projects
Fundora AI
Production ML

Fundora RL Engine

Reinforcement learning pipeline powering startup-investor matching at scale.

About the Project

The Fundora RL Engine is a production reinforcement learning system that powers startup-investor matching at scale. The agent learns optimal matching policies by observing the outcomes of introductions (meetings booked, deals closed) and continuously improves its recommendations. This is the core ML algorithm that runs Fundora's matching platform.

Key Features

  • RL-based matching algorithm for startup-investor pairing
  • Learns from feedback: meetings, follow-ups, and deal closures
  • State representation includes founder profiles and interaction history
  • Reward signal based on successful matches and conversions
  • Production system powering vest-fundora.com

Impact

Powers the live matching engine at vest-fundora.com. Continuously learning from real-world feedback to improve match quality.

Tech Stack

PyTorchFastAPIPostgreSQLRedis

Metrics

Production system
Powers Fundora matching

Interested in this project?

Let's discuss how I can build something similar for you.