Staff Machine Learning Engineer - Ads Bidding & Pacing

Summary

At Apple, we focus deeply on our customers’ experience. Apple Ads brings this same approach to advertising, helping people find exactly what they’re looking for and helping advertisers grow their businesses. Our technology powers ads and sponsorships across Apple Services, including the App Store, Apple News, and MLS Season Pass.

Everything we do is designed for trust, connection, and impact: We respect user privacy, integrate advertising thoughtfully into the experience, and deliver value for advertisers of all sizes—from small app developers to big, global brands. Because when advertising is done right, it benefits everyone.

We are seeking a self-motivated individual that will build out the next generation of our ads platforms and ensure that Apple provides the most relevant and high quality ads experience while maintaining a healthy marketplace. You should have experience developing and implementing machine learning or optimization algorithms, ideally within the ads space, recommendations, or search relevance. You will have an excellent understanding of scalable architectures and thrive working in Agile environments.

About the role

In this role, you will design and build scalable solutions that enable advertisers to optimize for their campaign goals and performance on the Apple Ads. You will have the opportunity to build the next generation solutions for budget and bid optimization that enable driving optimal campaign performance and advertiser experience. You will have the opportunity to apply your ability to move the state of the art techniques in a fast growing business that positively impacts publishers, developers and Apple users at global scale. The ability to be a great teammate under tight deadline constraints is key to success.

Responsibilities

You will develop models and systems that improve our platform across the board, develop production code to generate high quality ad recommendations and work closely with business partners to help drive the development of new products as well as perform large scale and complex experiments to understand their effects.

• You will drive strategic outcomes through substantial innovation in multiple fields by leading the development and application of advanced techniques and algorithms to improve our ad network.
• You have, or will develop a deep understanding of the ad network behavior, and will work with product management and business leadership to prioritize an innovation roadmap across multiple technical domains.
• You will lead the conception, development, and delivery of state of the art capabilities that differentiate our products and are core to our business.
• You will work with a variety of cross functional business partners to set strategy and bring end-to-end solutions that scale as we grown.

Minimum Qualifications

• 8+ years of experience building machine learning and quantitative optimization capabilities across many different product areas at scale
• Experience in machine learning, quantitative methods, control systems, or reinforcement learning
• Ability to apply and implement research concepts, ultimately in production quality code
• Experience defining clear, testable research hypotheses, including intended impact on the business
• Deep knowledge of design of experiments, online experimentation approaches, preferably at scale
• Ability to formulate and advocate for R&D objectives and results to cross-functional team members including executive business leadership and product management
• Experience contributing and/or reviewing research for top conferences and publications
• Deep fluency in Java or Python.
• Experience with Spark, Hadoop or other distributed frameworks.

PhD in Machine Learning, Statistics, Control Theory, Forecasting, Optimization, Reinforcement Learning or related field with experience building production systems or have equivalent experience working with large data science / machine learning projects in industry.

Preferred Qualifications

Experience in ads optimization, recommendations, or search relevance optimization is highly preferred