Senior System Engineer - AI Inference & GPU Performance

United States Digital Space LLC; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learningOpportun it

Job summary

United States Digital Space LLC is seeking a highly skilled engineer to advance our AI inference platform. You will develop and optimize low-level kernels and runtime components, focusing on performance on GPU platforms, and collaborate with ML and backend teams to streamline end-to-end execution.

You should have strong C++ proficiency or deep GPU programming expertise, plus hands-on experience with profiling and debugging tools and a solid understanding of CPU/GPU memory hierarchies.

Qualifications

• Strong proficiency in C++ or GPU programming with high-performance focus.
• Experience in GPU programming or systems-level software development.
• Hands-on experience with profiling and debugging tools on CPUs and GPUs.
• Solid understanding of CPU/GPU architecture and memory hierarchy.

Responsibilities

• Develop and optimize low-level kernels and runtime components for AI inference.
• Improve performance of inference engines on GPU platforms.
• Profile and debug system-level and hardware-level performance issues.
• Integrate support for new hardware architectures (Hopper, Blackwell, Rubin).
• Collaborate with ML and backend teams to optimize end-to-end execution.

Skills

C++ proficiency

GPU programming

Memory management

Systems-level software

Profiling and debugging

Tools

perf

VTune

Nsight

ROCm profiler

Job description

United States Digital Space LLC is seeking a highly skilled engineer to advance our AI inference platform. You will develop and optimize low-level kernels and runtime components, focusing on performance on GPU platforms, and collaborate with ML and backend teams to streamline end-to-end execution.

You should have strong C++ proficiency or deep GPU programming expertise, plus hands-on experience with profiling and debugging tools and a solid understanding of CPU/GPU memory hierarchies.