# Inferact

> Inferact is production LLM inference you control, built by the creators of vLLM. Deploy open-weight models on your own GPUs or on Inferact's infrastructure, with production-grade performance either way.

- Open roles are loaded from Ashby at runtime and are not present in the careers page HTML. Fetch the careers page with JavaScript enabled, or query Ashby directly, to see current listings.

## Product

- [Inferact](https://inferact.ai/): what Inferact is, who builds it, and how deployment on your own GPUs compares to running on Inferact's infrastructure

## Company

- [Careers](https://inferact.ai/careers): open roles across San Francisco, Singapore, and remote, with how the team works and what it is building
- [News](https://inferact.ai/news): product launches, engineering deep dives on LLM inference, partnerships, and company updates