Our Customer:

Our client is a forward-thinking early-stage startup creating next-generation GPU efficiency solutions and developing performance layers for AI and LLM workloads..

Your tasks:

Design and enhance GPU software infrastructure.
Work with CUDA, OpenCL, ROCm, and LLVM to boost computational performance.Drive code compilation and transformation workflows from CPU to GPU.
Develop scalable high-performance computing and AI infrastructure layers.Collaborate with top-tier engineers across GPU, AI, and compiler domains.

Required Experience and Skills:

5+ years of hands-on experience working with GPU, compiler, or HPC technologies.
Strong expertise in performance tuning, GPU memory management, and computer architecture.
Expertise and passion for performance, latency, and optimization.
Would be a plus:Experience with HPC, LLM systems, or AI infrastructure.