Sr. AI Inference Platform Engineer

Apple • Seattle, WA

2h

About The Position

Build tooling, automation, and analysis capabilities to strengthen Apple’s AI inference platform. The role focuses on developing performance benchmarking systems, capacity projection models, and data analysis pipelines that inform AI infrastructure teams and capacity planners. It combines AI systems performance, distributed infrastructure, and software engineering to support data-driven decisions about scaling and optimizing the inference platform.

As part of Apple’s next-generation datacenter engineering team, the engineer will design and build tools and analysis systems that provide a real-time picture of performance across the fleet. The work will inform hardware investment, help detect regressions before they reach production, and support capacity forecasting months in advance. This is a cross-functional role focused on complex, large-scale infrastructure challenges.

Requirements

• Bachelor’s or master’s degree in Computer Science or a related technical field.
• Solid understanding of AI/ML inference architecture and serving-system performance characteristics.
• At least 7 years of experience in performance and infrastructure engineering in distributed systems.
• At least 7 years of coding experience in Python, Go, C++, or other programming languages.
• Experience with automation engineering, tooling, and data pipelines supporting engineering workflows.
• Strong knowledge of GPU/accelerator architecture as it relates to AI workloads.
• Practical statistical knowledge applicable to performance analysis and forecasting.
• Excellent communication skills and ability to turn data into clear guidance for infrastructure teams and capacity planners.

Nice To Haves

• Experience with performance benchmarking and methodologies for AI/ML inference systems.
• Familiarity with capacity planning and forecasting or projection models for large-scale infrastructure.
• Experience with GPU profiling and observability tools, such as Nsight or other vendor-specific profilers.
• Experience with data visualization and reporting tools or frameworks for surfacing performance trends to stakeholders.
• Familiarity with ML serving frameworks and runtimes, such as Triton, TensorRT-LLM, or vLLM.
• Experience with CI/CD and workflow orchestration tools for building automated performance analysis pipelines.
• Knowledge of cluster schedulers and orchestration platforms, such as Kubernetes.
• Experience with metrics and logging tools, such as Prometheus, Grafana, or Splunk.

Responsibilities

• Build tooling, automation, and analysis capabilities for the AI inference platform.
• Develop performance benchmarking systems, capacity projection models, and data analysis pipelines.
• Provide engineers and capacity planners with a real-time picture of performance across the fleet.
• Inform hardware investment and infrastructure scaling and optimization decisions.
• Help detect performance regressions before they reach production.
• Forecast infrastructure capacity needs months in advance.
• Turn raw data and analysis into clear guidance for infrastructure teams and capacity planners.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior