Role Overview :
We are seeking an experienced System Engineer (67 years) with strong expertise in C programming, NVIDIA GPU development, and CUDA stack integration. This role involves working on GPU kernel drivers, CUDA stack management, memory frameworks, and kernel task execution to optimize GPU performance for large-scale AI infrastructure. The ideal candidate will have deep hands-on experience in NVIDIA GPU engineering and low-level system programming.
Key Responsibilities :
- Design, develop, and optimize GPU kernel drivers and integrations with the NVIDIA CUDA stack.
- Work on CUDA memory management, including unified memory frameworks and efficient GPU memory access.
- Implement and fine-tune GPU CUDA kernel task execution for performance and scalability.
- Debug, profile, and optimize low-level GPU interactions to ensure reliability and efficiency.
- Collaborate with platform, infrastructure, and API engineering teams to integrate GPU system capabilities into the broader Hosted.ai platform.
- Stay updated with NVIDIA GPU advancements, driver updates, and CUDA releases to continuously enhance platform 67 years of engineering experience with strong focus on NVIDIA GPU and CUDA stack development.
- Proficiency in C / C++ programming for low-level systems and kernel development.
Hands-on experience with :
GPU kernel drivers and CUDA integrationMemory access, allocation, and unified memory frameworksGPU task scheduling and CUDA kernel execution flowsStrong debugging, profiling, and performance optimization skills for GPU workloads.Solid understanding of Linux kernel internals and system-level programming.Ability to work in cross-functional teams and contribute to highly complex system design discussions.(ref : hirist.tech)