GPU Systems Performance Engineer for AI Inference

Yoh Services LLC; California (MO); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Medical benefits

Dental & Vision

401K Retirement

Job summary

Yoh Services LLC is seeking a hands-on Performance/ Benchmark Engineer to characterize and optimize AI workloads on large-scale NVIDIA GPU infrastructure, including DGX and B200/B300 systems. You will focus on GPU compute performance, AI inference, and system benchmarking while collaborating across architecture, compute, and networking teams.

The role requires deep hands-on GPU benchmarking experience, strong Python scripting, and proficiency with CUDA/NCCL.

Qualifications

• Deep hands-on experience with NVIDIA GPU compute platforms and AI/ML performance benchmarking.
• Strong understanding of AI inference, model performance, workload characterization, and GPU architecture.
• Experience with NVIDIA DGX, B200/B300, H100/H200, Blackwell, Hopper, or comparable GPU systems.
• Experience analyzing performance metrics including latency, throughput, GPU utilization, memory bandwidth, and multi-GPU scaling.
• Strong scripting and automation skills using Python or similar languages.

Responsibilities

• Develop and execute performance benchmarks for AI inference and machine learning workloads across NVIDIA GPU systems.
• Characterize performance on platforms including NVIDIA DGX and B200/B300-based systems, analyzing throughput, latency, utilization, memory behavior, and scaling efficiency.
• Evaluate AI models and workload configurations to identify performance bottlenecks and recommend system or architecture improvements.
• Build benchmarking methodologies, automation, and reporting frameworks to produce repeatable performance results.
• Collaborate with architecture, compute, networking, and software teams to optimize end-to-end AI cluster performance.

Skills

NVIDIA GPU

AI benchmarking

Python scripting

Performance analysis

Education

BS in CS/EE

Tools

CUDA

NCCL

TensorRT

PyTorch

Nsight

Job description

Yoh Services LLC is seeking a hands-on Performance/ Benchmark Engineer to characterize and optimize AI workloads on large-scale NVIDIA GPU infrastructure, including DGX and B200/B300 systems. You will focus on GPU compute performance, AI inference, and system benchmarking while collaborating across architecture, compute, and networking teams.

The role requires deep hands-on GPU benchmarking experience, strong Python scripting, and proficiency with CUDA/NCCL.