Leading AI development at RedBit. Building intelligent tools and helping clients figure out if/how they can leverage AI.

Currently building:

  • AI-powered pre-screening and interview scheduling for recruiters
  • AI-powered product feedback gathering & analysis
  • automated product image generation tools for e-commerce stores
  • intelligent contract bidding platform
  • data analytics platform for water meters
  • automated invoice management


Graduate student supervised by Prof. Xiaodan Zhu at Queen's University Ingenuity Lab.

Working with JP Morgan AI Research on financial applications of LLMs. Recently accepted paper at FinNLP and preparing another for EMNLP.

Previously, worked with Prof. Christian Muise on macq, a python library for planning action model acquisition and published a paper on it at ICAPS 2022.


I love exploring latent space, and following others' experiments.

Language models are so much more than simple tools, they are an embodiment of the aggregate human subconscious (an approximation of the ~entire internet). By exploring hidden parts of the distribution you can uncover some fascinating stuff.

Especially interested in feature steering right now. If you have cool resources on feature steering in open-source models please share!

I'm also a linux hobbyist. Recent arch to nixos convert, my dotfiles are a never-ending labour of love. I have a somewhat popular neovim config featuring a custom llm chat plugin.

My computer is an extension of myself.