Osmosis
Reinforcement Learning (RL) for AI Agents
Inaajiri
Kuhusu
Maelezo ya kampuni kwa Kiingereza
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.
Mada
- Eneo
- San Francisco, CA, Marekani
- Ukubwa wa timu
- Wafanyakazi: 6
- Kundi la YC
- Winter 2025
- Hali
- Inafanya kazi
- Hatua
- Hatua za awali
