RunRL docs · Oct 2025
Official product update announcing LoRA support, automatic MoE detection, dataset wizard beta, REST API parity with the UI, SFT warmups, and MCP tool support.
Company research
Public company, workplace, funding, and market signals
Updated Jul 30, 2026
Overview
RunRL is a San Francisco-based YC Spring 2025 startup building reinforcement learning as a service for improving LLMs and AI agents with custom reward functions and RL fine-tuning.
Primary product
Reinforcement learning as a service platform for training and improving LLMs and AI agents
Founded
2025
Headquarters
San Francisco, California, United States
Team size
1-10
Industry
Artificial intelligence
Sub-industry
Reinforcement learning platform / AI agent optimization
Business model
SaaS
Open Positions
0 jobs at RunRL
No open positions
Check back later for new openings