Staff ML Engineer - Ads ML Infrastructure

At Apple, we work every day to create products that enrich people’s lives. Our Ad Platforms group makes it possible for people around the world to easily access informative and imaginative content on their devices while helping publishers and developers promote and monetize their work. Today, our technology and services power advertising in Search Ads, App Store, and Apple News. Our platforms are highly-performant, deployed at scale, and setting new standards for enabling effective advertising while protecting user privacy.

The Machine Learning Platform team’s mission is to empower Ad Platforms teams to build and scale the innovative ML systems that deliver highly optimized advertising content to consumers. Are you a results-oriented and versatile engineer who can excel in an Agile environment? You will work closely with engineers and data scientists to design, develop, and build world-class platform capabilities that will enable Ad Platforms teams to improve and scale our ML features, models, and applications.

The ML Platform team is responsible for bringing numerous features to advertisers and consumers while simultaneously supporting scalable modeling and continuous experimentation by all Ad Platforms teams. As a key contributor to this team, you will design and develop secure and scalable back-end systems. You will enjoy building high-performing, elegant systems from the ground up, in close partnerships with various teams. You will also possess keen judgment in selecting technologies and building the right solution for the interesting challenges we get to tackle here. You will have the opportunity to define and refine architectures to meet the unique ad network challenges we must solve. You will play a meaningful role building machine learning products which deliver on Apple's privacy commitments and change the way advertising works with data.

Join us and contribute to a culture that emphasizes reliability, simplicity, and scalability. You will join a team of world-class machine learning engineers hungry to apply leading-edge technologies to deliver extraordinary experiences to our customers. We are one team, nurturing each other’s growth and supporting each other in delivering for our customers!

Minimum Qualifications

• Proven track record of designing and operating large-scale, low-latency ML Serving platform supporting real-time and batch inference.
• Experience of model quantization, tensor parallelism, and inference optimizations (e.g ONNX Runtime, TensorRT, vLLM). Actively led evaluation and adoption of such technologies.
• Experience working on distributed systems (e.g Ray, high-throughput RPC systems) to support scalable inference workloads and hybrid online/offline serving patterns.
• Hands-on experience designing and optimizing low-level GPU kernels to maximize hardware utilization, bypass memory bandwidth bottlenecks, and accelerate deep learning primitives.
• Prior experience in advertising industry, federated learning and privacy-preserving ML techniques.
• Recognized as a technical leader and mentor, supports the growth of engineers through code/design reviews, working groups, and internal knowledge sharing.
• Led development of foundational AI/ML platforms and tooling including Feature Stores, Vector DB to accelerate team productivity and model lifecycle management.
• Experience performance tuning & trouble-shooting.
• Passionate about developer experience builds abstractions, automation tools, and reusable components to streamline ML workflows and reduce operational burden.
• Ability to communicate effectively, both written and verbal, with technical and non-technical multi-functional teams.
• Results oriented with a desire to work in a fast-paced and collaborative work environment.

Preferred Qualifications

• PhD, MS, or BS in computer science or a related field, with 8+ years of experience in machine learning and strong software engineering skills.