Senior GPU Performance & Benchmark Engineer – AI Inference

Yoh,-A-Day-; Santa Clara (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Medical, Prescription, Dental & Vision

401K Retirement Savings Plan

Direct Deposit & weekly epayroll

Certification and training

Job summary

Yoh is seeking a hands-on Performance and Benchmark Engineer to characterize AI workloads on NVIDIA GPU systems in Santa Clara. You will scope, run, and optimize benchmarks across DGX and related platforms, focusing on latency, throughput, and scaling.

Collaborate with architecture, compute, and networking teams to drive end-to-end performance improvements while delivering repeatable results and clear reporting.

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 compute platforms

AI/ML performance benchmarking

Python scripting

Performance metrics

Tools

NVIDIA DGX

B200/B300 systems

H100/H200

Nsight

Job description

Yoh is seeking a hands-on Performance and Benchmark Engineer to characterize AI workloads on NVIDIA GPU systems in Santa Clara. You will scope, run, and optimize benchmarks across DGX and related platforms, focusing on latency, throughput, and scaling.

Collaborate with architecture, compute, and networking teams to drive end-to-end performance improvements while delivering repeatable results and clear reporting.