General Interest · Lower-power data-center inference
Frontier-model inference at a fraction of the power
The company
Inference is on track to become the largest computing workload behind Super Intelligence, and power is now the limit on how fast data centers can add capacity for it. Much of a chip’s energy goes to moving model data rather than computing with it.
This venture is building an inference chip that spends far less energy moving data and is designed for high-volume manufacturing. Its first chips already match the accuracy of conventional digital hardware, and the next generation is designed to run a full frontier model on a single module. It sells first to the largest inference buyers.
Read more in the first cohort announcement.
Who this listing is for
This listing is for people who want to work on this venture in a role that is not posted yet. As the company forms, it will hire across engineering, operations, and business.
If you have built in this industry, tell us what you do and which part of the company you would want to work on. We will reach out when a role that fits opens.
What happens after you apply
We keep your note on file for this venture and share it with the company as it starts hiring.
Express interest in this venture
Lower-power data-center inference
Tell us what you do and what you would want to work on, and attach your resume.
You will need your resume as a PDF or Word file.
Contact
For questions about this venture, or to arrange a conversation before applying, please reach out.
