Senior ML Engineer - Ads ML Infrastructure

Apple•New York City, NY

23h

About The Position

Apple’s Ad Platforms group builds advertising technology for Search Ads, the App Store, and Apple News, helping publishers and developers promote and monetize their work while protecting user privacy. The Machine Learning Platform team enables Ad Platforms teams to build and scale machine learning systems, features, models, and applications. As a key contributor, you will design and develop secure, scalable, high-performance back-end systems and platform capabilities for machine learning. You will work closely with engineers, data scientists, and other teams to support scalable modeling, continuous experimentation, and real-time and batch inference. The role includes defining and refining architectures, selecting technologies, and building foundational platforms and tools that improve ML workflows and model lifecycle management. You will also provide technical leadership and mentorship, helping foster a team culture focused on reliability, simplicity, scalability, and customer privacy.

Requirements

PhD, MS, or BS in computer science or a related field.
At least 6 years of experience in machine learning.
Strong software engineering skills.
Proven 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 optimization technologies such as ONNX Runtime, TensorRT, or vLLM.
Experience evaluating and adopting ML inference technologies.
Experience with distributed systems, such as Ray or high-throughput RPC systems, for scalable inference and hybrid online/offline serving.
Hands-on experience designing and optimizing low-level GPU kernels.
Experience in performance tuning and troubleshooting.
Ability to communicate effectively in writing and verbally with technical and non-technical cross-functional teams.
Results-oriented approach and ability to work in a fast-paced, collaborative environment.

Nice To Haves

Prior experience in the advertising industry.
Experience with federated learning and privacy-preserving machine learning techniques.
Recognized technical leadership and experience mentoring engineers.
Experience leading development of AI/ML platforms and tooling, including feature stores and vector databases.
Passion for improving developer experience through abstractions, automation, and reusable components.

Responsibilities

Design and develop secure, scalable back-end systems and ML platform capabilities.
Build and operate large-scale, low-latency ML serving systems for real-time and batch inference.
Evaluate and adopt technologies for model quantization, tensor parallelism, and inference optimization.
Develop distributed systems to support scalable inference workloads and hybrid online/offline serving patterns.
Design and optimize low-level GPU kernels to improve hardware utilization and accelerate deep learning primitives.
Lead development of foundational AI/ML platforms and tooling, including feature stores and vector databases.
Tune performance and troubleshoot systems.
Build abstractions, automation tools, and reusable components to streamline ML workflows and reduce operational burden.
Provide technical leadership and mentorship through code and design reviews, working groups, and internal knowledge sharing.
Collaborate and communicate with technical and non-technical cross-functional teams.