Inferact

Inferact is a company whose mission is to grow vLLM as an AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, the organization focuses on the intersection of AI models and hardware. Its software product, vLLM, provides high-throughput and memory-efficient inference and serving for large language models, aiming to make high-performance LLM deployment accessible across a wide range of hardware and open-source models.

The company serves developers, AI teams, and organizations seeking to deploy open-source models with integrated APIs and hardware efficiency. Its work in artificial intelligence and machine learning centers on optimizing model execution, low-level accelerator code, distributed serving, and cloud platforms. Core technological features include PagedAttention, advanced scheduling, and continuous batching designed to maximize GPU utilization and reduce inference costs.

The open roles indicate that Inferact is building teams comprising technical staff and co-op students across engineering functions. The open positions are located in San Francisco and include roles such as Member of Technical Staff (Forward Deployed Engineer) and Inference Engineering Co-op. These roles involve hands-on systems engineering, customer integrations, and work across the vLLM stack, ranging from inference runtimes and kernel engineering to performance and scale.