Sr. AI Inference Platform Engineer

We are looking for senior engineer to build tooling, automation, and analysis capabilities that strengthen our AI inference platform. This role will focus on developing sophisticated performance benchmarking systems, capacity projection models, and data analysis pipelines that directly inform our AI infrastructure teams and capacity planners. You'll work at the intersection of AI systems performance, distributed infrastructure, and software engineering to help the team make data-driven decisions about scaling and optimizing our inference platform. At Apple, we believe the future of AI is defined not just by models, but by the infrastructure that powers them. Our AI inference platform sits at the heart of products and experiences used by hundreds of millions of people worldwide, and we are building the systems that ensure it scales reliably, efficiently, and intelligently. As part of our next-generation datacenter engineering team, you will play a critical role in shaping how we understand, measure, and grow our AI infrastructure. You will design and build the tooling and analysis systems that give our engineers and capacity planners a clear, real-time picture of performance across our fleet. Your work will directly influence how we invest in hardware, how we detect regressions before they reach production, and how we forecast capacity needs months in advance. This is a high-impact, cross-functional role for an engineer who is energized by complexity, thrives on turning raw data into actionable insight, and wants to work on problems that matter at massive scale. Minimum 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. 7 or more years of experience with performance and infrastructure engineering in distributed systems. 7 years of experience coding in Python, Go, C , or other programming languages. Experience with automation engineering, tooling, and data pipelines to support 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. Preferred Qualifications: Experience with performance benchmarking and methodologies for AI/ML inference systems. Familiarity with capacity planning and forecasting/projection models for large-scale infrastructure. Experience with GPU profiling and observability tools (e.g., Nsight, other vendor-specific profilers). Experience with data visualization and reporting tools/frameworks for surfacing performance trends to stakeholders. Familiarity with ML serving frameworks and runtimes (e.g., Triton, TensorRT-LLM, vLLM, or similar). Experience with CI/CD and workflow orchestration tools for building automated performance analysis pipelines. Knowledge of cluster schedulers and orchestration platforms (e.g., Kubernetes). Experience with metrics and logging tools (e.g., Prometheus, Grafana, Splunk).