Reinforcement Learning (RL) for AI Agents
Companies struggle to post-train and fine-tune language models for specific tasks with better performance, cost, and latency than foundation models.
A CLI-based post-training platform that orchestrates compute, builds reward models, and runs observable reinforcement learning fine-tuning for language models.
Fast-growing AI companies and their developers building task- or domain-specific language models.
Currently: osmosis.ai Previously: gaming founder, VC
Defining how real time systems should be built. Previously worked on data architecture and ecosystem at TikTok recommendations as the 5th and youngest US hire




