AI Infrastructure Engineer

Experteer Overview In this role you will push LLM inference on Intel GPUs to peak performance. You will work across the stack, profiling bottlenecks, developing high-performance kernels, and upstreaming optimizations into open-source projects like vLLM and SGLang. You’ll shape hardware roadmaps through data-driven analysis and cross-team collaboration. This is a hands-on, impact-driven position that ties AI workloads to Intel’s hardware strategy. Compensation / Benefits * Own end-to-end optimization of running state-of-the-art LLMs on Intel GPUs * Profile, diagnose, and resolve cross-stack performance bottlenecks * Design, write, and optimize custom high-performance kernels for attention, MoE, quantization, and operator fusions * Upstream architectural improvements into open-source repos like vLLM, SGLang, and PyTorch * Collaborate with architecture and compiler teams to shape future GPU roadmaps based on GenAI workloads * Promote AI infrastructure and performance optimization initiatives Tasks * 4+ years of software engineering experience in GPU computing, AI systems, or HPC (or 3+ years with a Masters, or PhD) * Proficiency in modern C++ and Python * Ability to read and modify complex systems-level code Key requirements * competitive pay * stock bonuses * health insurance * retirement plan * vacation

GenAI Tasks * 4+ years of software engineering experience in GPU computing, AI systems, or HPC (or 3+ years with a Masters, or PhD) * Proficiency in modern C++ and Python * Ability to read and modify complex systems-level code Key requirements * competitive pay * stock bonuses * health insurance * retirement plan * vacation