morgane moss

I am an applied ML researcher and engineer, specializing in reinforcement learning for reasoning and agentic models. I’m in the post-training team at Nous Research.

I work on credit assignment and search for long-horizon tasks such as deep research. I am also interested in unlocking synthetic data generation. I was advised by Rishabh Agarwal and Aaron Courville at Mila, and Alessandro Sordoni at Microsoft Research. I arrived at RL from computational neuroscience, modelling optimal policy learning in natural neural networks.

My publications are listed on Google scholar.

highlights

NSERC Canada Graduate Scholarship ($120k, 2026) · Mila Excellence Scholarship ($24k, 2024) · Microsoft Hackathon category winner, 1st of 479 (2025)