
11 - 50 employees
Founded 2025
🤖 Artificial Intelligence
🤝 B2B
🏢 Enterprise
Artificial Intelligence • B2B • Enterprise
Inferact is a startup founded by the creators and core maintainers of vLLM, the leading open-source LLM inference engine. The company aims to accelerate AI progress by making model inference cheaper and faster, expanding vLLM's performance and support for emerging architectures and accelerator hardware. Inferact combines deep expertise at the intersection of models and hardware to provide inference infrastructure used by research labs, hyperscalers, and startups, while continuing to develop and contribute optimizations back to the open-source community.
đź•’ March 18
Exceptional generalist engineers for AI inference engine development, optimizing CUDA kernels and designing distributed systems. Fully remote opportunity with a focus on autonomy.