TrainLoop
Reasoning Fine-Tuning
Y CombinatorWinter 2025ActiveB2BEngineering, Product and DesignDeveloper ToolsGenerative AIReinforcement Learning
What they do
Problem
Developers struggle to efficiently improve and fine-tune LLM reasoning performance using reinforcement learning.
Solution
TrainLoop provides a reinforcement learning-based fine-tuning platform that makes it easy to boost LLM performance.
Who it's for
Developers and ML teams building and deploying LLM-powered applications.
Founders
Jackson Stokes
Founder
Cofounder at TrainLoop, previously Google Gemini & AlphaFold performance
Mason Pierce
Cofounder / CTO
My background is in applying AI models to business use-cases and have always found fine-tuning to be way harder than it should be - My mission is to unlock fine-tuning for all builders :)
Company timeline
- Founded2025
- YC batchWinter 2025
- StatusActive
- Team size6 people
- LocationSan Francisco, CA, USA
