Osmosis
Reinforcement Learning (RL) for AI Agents
y-combinatorWinter 2025Artificial IntelligenceMachine LearningReinforcement LearningInfrastructure🇺🇸 San Francisco6 peoplehiring
Andy Lyu, Kasey Zhang · 2 co-founders
Profile coverage4 of 8 · missing Funding, Signals, Customers, Stack / tools · last run 8/10/2026
About
Osmosis is a post-training platform that helps companies fine-tune language models using reinforcement learning. We work with fast-growing AI companies to train task/domain-specific models that beat foundation models on performance, cost, and latency. Our platform handles compute orchestration, reward modeling, and training run observability as a CLI-based product usable by developers and agents.