Product
Hardware
Library
Sand to Thought
Careers
Docs
Book a call
Log in
The research lab focused on inference.
Training
Automatic fine-tuning from your traffic.
Inference
Open-model inference, pay based on your latency requirement.
Models
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash
GLM-5.3 Flash
GLM-5.3 Flash
K
Kev 9B
Kev 9B
Notes
Frontier notes on inference, systems and hardware.
Methods
How we operate, and why.
Latest writing
Announcing Carat: An inference engine designed for Gemma 4
Sep 2, 2026
Thesis
Jul 13, 2026
Affordable and open intelligence
Sep 9, 2026
See all writing
Careers
We
are
hiring.
Founding Infrastructure Engineer
We only succeed if the infrastructure underneath is fast, efficient and reliable. Right now nobody fully owns it. We need a founding engineer who has run infrastructure at scale and has also built from scratch at a seed-stage startup. This person will own the GPU fleet, the serving stack and its reliability as we go from private beta to real traffic, and scale beyond.
Engineering
·
Remote | West Coast (GMT -7 to GMT -8)
Founding Silicon Engineer
Design model-specific inference hardware from performance modeling through RTL and verification.
Silicon
·
Cambridge
Head of Silicon
Define our silicon direction and build a team for model-specific inference hardware.
Silicon
·
Cambridge
Founding Inference Research Engineer
Find and remove bottlenecks across model representation, GPU kernels, runtimes, and serving for open-weight models.
Inference research
·
Cambridge
Engineer Journalist
Turn research on models, inference, and hardware into work that helps engineers understand the stack they rely on.
Team
·
Cambridge