Senior LLM Platform Engineer — MLOps for Production

Apple Inc.; San Francisco (CA); On-site; USD 185,000 - 325,000; Full time

Benefits offered by this job

Medical and dental coverage

Retirement benefits

Employee stock purchase plan

Discounted products and services

Tuition reimbursement

Relocation assistance

Bonus/commission potential

Job summary

Apple Inc. seeks an experienced ML Engineer to own the full model lifecycle, from experimentation through deployment to retirement, with strong governance and privacy by design.

You will build scalable ML infrastructure, orchestration, and observability, collaborating across data scientists, frontend engineers, and Trust & Safety to deliver reliable LLM-powered features at scale. You will optimize models for production, tune for latency and throughput, implement robust versioning, and ensure

Qualifications

• Master's degree in CS, engineering, or related field.
• 8+ years in ML and software engineering with production ML/LLM systems.
• Proven track record shipping production-grade ML/LLM systems.
• Strong understanding of LLMs, fine-tuning, prompt engineering, and RAG patterns.
• Experience building pipelines processing multimodal data and integrating ML inference.
• Hands-on production deployment of LLMs/ML models with runtimes/compilers.
• Experience with distributed systems, AWS, Kubernetes, CI/CD, and Spark data pipelines.
• Excellent communication and collaborative mindset.

Responsibilities

• Own the full model lifecycle from experimentation to retirement with governance.
• Fine-tune models, including adapters/LoRA and distillation targets.
• Design scalable ML infrastructure and experimentation platforms with dashboards.
• Define and implement CI/CD for model deployment, versioning, and monitoring.
• Optimize production models for throughput, latency, and cost targets.
• Drive model observability, incident response, and SLAs for AI products.
• Build frameworks measuring quality, reliability, latency, and cost of serving.

Skills

Python

Java/Scala

Kubernetes

Cloud/AWS

ML/LLM systems

LLMOps

PyTorch/TensorRT

Go or similar (bonus)

Education

Master's degree

Tools

Flask

FastAPI

ONNX Runtime

TensorRT

TorchServe

Kubernetes

Airflow

MLflow

Weights & Biases

Delta Lake

DVC

Job description

Apple Inc. seeks an experienced ML Engineer to own the full model lifecycle, from experimentation through deployment to retirement, with strong governance and privacy by design.

You will build scalable ML infrastructure, orchestration, and observability, collaborating across data scientists, frontend engineers, and Trust & Safety to deliver reliable LLM-powered features at scale. You will optimize models for production, tune for latency and throughput, implement robust versioning, and ensure