Senior AI Inference Platform Engineer — Benchmarking

Apple; Seattle (WA); On-site; USD 175,000 - 309,000; Full time

Benefits offered by this job

Employee stock programs

Employee Stock Purchase Plan

Medical and dental coverage

Retirement benefits

Discounted products

Tuition reimbursement

Discretionary bonuses

Job summary

Apple seeks an engineer to build tooling, automation, and analysis capabilities for the AI inference platform, focusing on benchmarking, capacity projection models, and data pipelines that inform infrastructure teams and capacity planners.

You will design real-time performance dashboards, collaborate with AI infrastructure engineers, hardware teams, and capacity planners to forecast needs months in advance, and help accelerate data-driven decisions for scaling AI workloads.

Qualifications

• BS or MS in Computer Science or related technical field.
• Solid understanding of AI/ML inference architecture and the performance characteristics of serving systems.
• Experience with performance and infrastructure engineering in distributed systems.

Responsibilities

• Design and build automations to evaluate AI inference performance across hardware generations and configurations.
• Develop tooling to surface performance trends, regressions, and insights to infrastructure and planning teams.
• Build projection and forecasting models to support long-term capacity planning decisions.
• Analyze performance and utilization data to identify bottlenecks, trends, and optimization opportunities.
• Partner with AI infrastructure engineers, hardware teams, and capacity planners to deliver critical data and tooling.
• Create and enhance performance analysis workflows to increase team velocity and data reliability.
• Continuously improve the accuracy, coverage, and usability of performance measurement and analysis systems.

Skills

Python

Go

C++

Education

BS or MS in Computer Science

Tools

Nsight

Prometheus

Grafana

Job description

Apple seeks an engineer to build tooling, automation, and analysis capabilities for the AI inference platform, focusing on benchmarking, capacity projection models, and data pipelines that inform infrastructure teams and capacity planners.

You will design real-time performance dashboards, collaborate with AI infrastructure engineers, hardware teams, and capacity planners to forecast needs months in advance, and help accelerate data-driven decisions for scaling AI workloads.