Jobs

Inferact is seeking a Member of Technical Staff, Performance and Scale, to build distributed systems for global-scale AI inference using vLLM. This infrastructure engineer will design foundational layers for serving models across thousands of accelerators with minimal latency and maximum reliability. The ideal candidate will have strong systems programming skills in Rust, Go, or C++ and experience with high-performance distributed systems. This role is crucial for making frontier model deployment as straightforward as spinning up a serverless database.