Software Engineer, Model Runtime

Join the scaling team to architect and implement the next generation of production-grade model runtimes. This role demands deep systems knowledge as you build foundational infrastructure that dictates performance limits for our state-of-the-art models. You will focus on optimizing the entire inference stack—from GPU memory management and kernel execution to request scheduling across heterogeneous compute resources. Key responsibilities include improving startup time, reducing memory footprint, and ensuring determinism in massive distributed environments. Experience with low-level languages (C++, Rust) and hardware-specific APIs is crucial for developing reliable, highly efficient model serving backends that power global AI services.

(تازہ ترین نوکریاں، سلیبس اور ٹیسٹ کی تیاری کی مکمل معلومات)