Let's advance the frontier of AI inference
Building the frontier of AI inference
Our mission is to accelerate AI progress by advancing vLLM and building the infrastructure needed to make frontier inference faster, more efficient, and more accessible.
44:14 min
Building the Infrastructure That Runs Modern AI
Watch our founders discuss the founding of Inferact
Build in the open
vLLM has always been built in the open, and the optimizations we develop flow back to the community for everyone building AI.
Research is the product
Models, architectures, and hardware keep changing, so inference is never solved. Our research turns research into production improvements in speed, efficiency, and scale
Grow with the ecosystem
We work alongside model labs, hardware makers, and thousands of open-source contributors to optimize frontier inference.
Where frontier inference research meets production
San Francisco
Our headquarters in San Francisco, the heart of the AI community.
Singapore
Our APAC hub in downtown Singapore, close to the model labs and partners we work with across Asia.
Remote
Select roles are open to remote candidates, with occasional travel to our San Francisco or Singapore offices.
Join us. XX Job openings
Working at inferact
Hiring process
We'll match your pace, having gone from first call to offer in three business days with most processes taking on average 2–3 weeks.
Running at volume?
Tell us a model to serve. We'll help optimize it.
.avif)
.png)
