# Inferless Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/inferless
> Markdown URL: https://aitinkerers.org/technologies/inferless.md
> Technology record last updated: 2026-03-05T10:24:53Z
> Generated: 2026-10-24T07:59:35Z

Inferless is the serverless GPU platform for blazing-fast, cost-efficient deployment of machine learning models with zero infrastructure overhead.

Inferless, co-founded by Aishwarya Goel and Nilesh Agarwal in 2023, is a serverless GPU inference platform that eliminates complex ML deployment workflows. It allows developers to deploy custom models instantly from sources like Hugging Face or AWS S3, ensuring ultra-low cold starts and automatic scaling from zero to hundreds of GPUs. Backed by investors including PeakXV Partners (formerly Sequoia) and Antler, the platform delivers significant financial benefits: clients have reported up to 90% savings on GPU costs compared to traditional cloud setups. This efficiency lets engineering teams focus on model building, not infrastructure management.

- Official technology site: https://www.inferless.com
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [How to use Open Source frameworks for Serverless Inference Deployment](https://sf.aitinkerers.org/talks/rsvp_SB7HgWS1kBA)

- Event context: AI Tinkerers SF - September Meetup🤖🔄🧠 — 2023-09-22 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_SB7HgWS1kBA

## Related Technologies

- [Containerization](https://aitinkerers.org/technologies/containerization) ([Markdown](https://aitinkerers.org/technologies/containerization.md)) — 3 public demos
- [Serverless](https://aitinkerers.org/technologies/serverless) ([Markdown](https://aitinkerers.org/technologies/serverless.md)) — 4 public demos
- [Triton Inference Server](https://aitinkerers.org/technologies/triton-inference-server) ([Markdown](https://aitinkerers.org/technologies/triton-inference-server.md)) — 2 public demos