ML Runtime Engineer (Mid-Level and Senior)
This role involves developing and integrating high-performance ML runtimes for Fractile's novel AI accelerator hardware, focusing on inference server integrations with open-source frameworks like PyTorch, vLLM, and SGLang. Engineers will work closely with hardware and ML teams using a co-design approach to optimise performance. The position emphasizes low-level runtime development in Rust and deep collaboration across software and hardware layers.