Sr. AI Inference Platform Engineer

What you'll do

• Automate evaluation of AI inference performance across hardware generations and configurations; surface trends, regressions, and insights.
• Build projection and forecasting models and analyze performance and utilization data to guide capacity planning and optimization.
• Partner with infrastructure, hardware, and planning teams to improve performance analysis workflows and measurement systems.

What they ask for

• BS or MS in Computer Science or a related technical field.
• Solid understanding of AI/ML inference architecture and serving-system performance; strong knowledge of GPU/accelerator architecture for AI workloads.
• 7 or more years of performance and infrastructure engineering experience in distributed systems.
• 7 years of coding experience in Python, Go, C++, or other programming languages; experience with automation, tooling, and data pipelines; practical statistical knowledge for performance analysis and forecasting.

Nice to have

• Experience with AI/ML inference benchmarking, capacity planning, GPU profiling, data visualization, ML serving frameworks, CI/CD, workflow orchestration, cluster schedulers, or metrics and logging tools.
• Examples named include Nsight, Triton, TensorRT-LLM, vLLM, Kubernetes, Prometheus, Grafana, and Splunk.

Pay

$175,000 and $308,500 (base salary)

Tools

Python, Go, C++, Nsight, Triton, TensorRT-LLM, vLLM, Kubernetes

AI focus

Develops and analyzes systems for AI/ML inference performance, benchmarking, infrastructure scaling, and capacity forecasting.