Staff ML Systems Engineer: Inference & Infra Leader

Apple, Inc.; San Francisco (CA); On-site; USD 216,000 - 325,000; Full time

Benefits offered by this job

Stock programs

Relocation assistance

Education reimbursement

Medical and dental coverage

Job summary

Apple, Inc. in San Francisco, CA, seeks a Staff Machine Learning Engineer to build inference systems and shared ML infrastructure for customer‑facing products. You will own architectural decisions and deliver across teams, with opportunities to extend into training and device‑to‑cloud integration.

You will lead projects spanning model inference, data processing, and deployment, while mentoring engineers and aligning cross‑functional teams for scalable production systems.

Qualifications

• Bachelor’s degree in CS/CE/IS/EE with 12+ years of relevant work experience.
• Experience shipping production ML systems with ownership of architecture.
• Strong software engineering including API design, testing, and debugging.
• Experience integrating ML models into software systems and deployment.
• Demonstrated history leading technical initiatives across teams.

Responsibilities

• Build inference systems for product workloads and APIs; optimize latency and throughput.
• Develop shared ML infrastructure across models and apps.
• Scale fine-tuning and training workflows with distributed job execution.
• Build data-processing workflows to prepare large training inputs.
• Connect ML systems with product software for on‑device and cloud use.
• Set technical direction, align interfaces, and lead prototyping to production.
• Mentor engineers through design reviews and implementations.

Skills

Production ML systems

Model inference

Distributed computing

System design

Leadership

Communication

Python

Education

Bachelor’s degree in CS/CE/IS/EE

Master’s degree in CS/CE/IS/EE

Tools

Ray

Ray Serve

ONNX Runtime

Core ML

Spark

Flink

LangGraph/MCP

Job description

Apple, Inc. in San Francisco, CA, seeks a Staff Machine Learning Engineer to build inference systems and shared ML infrastructure for customer‑facing products. You will own architectural decisions and deliver across teams, with opportunities to extend into training and device‑to‑cloud integration.

You will lead projects spanning model inference, data processing, and deployment, while mentoring engineers and aligning cross‑functional teams for scalable production systems.