Osmosis
Reinforcement Learning (RL) for AI Agents
Stellt ein
Über das Unternehmen
Unternehmensbeschreibung auf Englisch
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.
Themen
- Standort
- San Francisco, CA, USA
- Teamgröße
- 6 Mitarbeitende
- YC-Batch
- Winter 2025
- Status
- Aktiv
- Phase
- Frühphase
