GPU kernel programming Jobs

D-Matrix Frontier Group is at the leading edge of LLM inference on heterogeneous hardware, working across the full stack from use case identification and kernel optimization to building proof-of-concept systems. We build the tools, runtimes, and frameworks that enable frontier AI models to run efficiently and cost-effectively on diverse hardware, including D-Matrix silicon, CPUs, GPUs, and custom accelerators. This applied research and engineering team moves fast, ships real systems, and collaborates directly with product and hardware teams to shape the roadmap. We are seeking end-to-end inference engineers who are comfortable taking a novel research idea to a deployed, optimized system, working at every layer of the inference stack from kernel-level optimization to distributed orchestration and high-level serving APIs.

$195k - $285k