Senior ML Platform Engineer — Ads Infra with Equity

Apple, Inc.; New York (NY); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Stock programs

Bonuses/commission

Relocation

Healthcare & retirement

Job summary

Apple seeks a results-oriented ML Platform Engineer to design and develop scalable back-end systems for advertising platforms in New York City. You will collaborate with engineers and data scientists to deliver high-performance ML features, models, and experiments that respect user privacy.

You will lead architecture decisions, optimize GPU kernels, and guide teams in deploying scalable ML solutions at scale.

Qualifications

• Experience designing and operating large-scale low-latency ML serving platforms for real-time and batch inference.
• Experience with model quantization, tensor parallelism, and inference optimizations (ONNX Runtime, TensorRT, vLLM).
• Experience with distributed systems (e.g. Ray) to support scalable inference workloads.
• Hands-on experience designing and optimizing low-level GPU kernels for performance.
• Background in advertising, federated learning, and privacy-preserving ML is a plus.
• Proven ability to mentor engineers through reviews and knowledge sharing.

Responsibilities

• Design and develop secure, scalable back-end ML platform components for Ad Platforms teams.
• Collaborate with engineers and data scientists to deliver high-performance ML features and models.
• Define architectures and tooling to improve lifecycle management and developer experience.

Skills

ML Serving

Distributed systems

GPU kernels

Model quantization

Inference optimization

Federated learning

Privacy-preserving ML

Leadership & mentorship

Communication

Education

PhD/MS/BS in CS

Tools

Ray

ONNX Runtime

TensorRT

vLLM

Vector DB

Feature Stores

Job description

Apple seeks a results-oriented ML Platform Engineer to design and develop scalable back-end systems for advertising platforms in New York City. You will collaborate with engineers and data scientists to deliver high-performance ML features, models, and experiments that respect user privacy.

You will lead architecture decisions, optimize GPU kernels, and guide teams in deploying scalable ML solutions at scale.