AI Benchmarking and Telemetry Engineer - NVIS

What you'll do

• Develop and execute detailed benchmarking methods for large-scale GPU clusters.
• Build telemetry frameworks to capture system performance data across multiple levels.
• Deploy observability stacks including monitoring tools like Prometheus and Grafana.
• Collaborate with teams to define performance requirements and validate configurations.
• Maintain knowledge of industry-standard benchmarks in HPC and machine learning fields.
• Craft and implement telemetry solutions for large-scale distributed systems.

What we're looking for

• 8+ years of experience with HPC and AI infrastructure, including deployment and performance analysis.
• Deep expertise in Linux system administration and kernel tuning for large-scale systems.
• Proven experience crafting telemetry and monitoring solutions using tools like Prometheus and Grafana.
• Solid understanding of GPU architectures and CUDA programming principles for HPC/AI workloads.
• Proficiency in Python and Bash scripting for automation, data analysis, and workflow orchestration.
• Excellent analytical skills to interpret complex performance data and communicate findings effectively.