AI Inference Platform Performance Engineer

Socket.dev; Seattle (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Apple is seeking an engineer to build tooling, automation, and analysis capabilities for its AI inference platform. You will develop advanced performance benchmarking systems, capacity projection models, and data pipelines to inform capacity-planning and infrastructure decisions.

You will work at the intersection of AI systems performance, distributed infrastructure, and software engineering to turn raw data into actionable insight for scaling and optimizing the inference platform.

Qualifications

• BS or MS in Computer Science or related field.
• Strong understanding of AI/ML inference architecture and performance characteristics of serving systems.
• Experience with performance and infrastructure engineering in distributed systems.
• Proficiency in Python, Go, C++, or other languages.
• Experience with automation, tooling and data pipelines for engineering workflows.
• Strong knowledge of GPU/accelerator architecture for AI workloads.
• Practical statistics applicable to performance analysis and forecasting.
• Excellent communication skills to guide infrastructure teams.

Responsibilities

• Build tooling and analysis systems to monitor AI inference performance at scale.
• Develop benchmarking frameworks and capacity projection models for forecasting needs.
• Create data pipelines to support engineering workflows and capacity planning.
• Collaborate with AI infrastructure teams to inform hardware investments and scaling decisions.

Skills

AI/ML inference architecture

Distributed systems performance

Python/Go/C++ programming

Automation tooling

GPU/accelerator architecture

Statistical analysis

Clear communication

Education

BS or MS in Computer Science

Tools

Nsight

Prometheus

Grafana

Kubernetes

Job description

Apple is seeking an engineer to build tooling, automation, and analysis capabilities for its AI inference platform. You will develop advanced performance benchmarking systems, capacity projection models, and data pipelines to inform capacity-planning and infrastructure decisions.

You will work at the intersection of AI systems performance, distributed infrastructure, and software engineering to turn raw data into actionable insight for scaling and optimizing the inference platform.