Osmosis
Reinforcement Learning (RL) for AI Agents
Zaposluje
O podjetju
Opis podjetja v angleščini
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.
Teme
- Lokacija
- San Francisco, CA, Združene države Amerike
- Velikost ekipe
- Zaposleni: 6
- Generacija YC
- Winter 2025
- Status
- Aktiven
- Faza
- Zgodnja faza
