Principal Data Scientist

Yahoo serves as a trusted guide for hundreds of millions of people globally, helping them achieve their goals online through our portfolio of iconic products. For advertisers, Yahoo Advertising offers omnichannel solutions and powerful data to engage with our brands and deliver results.

A Little About Us:
We are an industry leading direct to Consumer and Ad tech solution for advertisers and publishers. Our innovative Ad tech gives one stop access to Yahoo, inc. trusted data, high quality inventory and demand, creative ad experiences and industry-leading machine learning, at global scale. Consumer Monetization team’s charter is to Find, Evaluate, Build, and Scale new monetization, subscription and internal campaign tools and products, ad formats and functionalities across all Yahoo brands including Yahoo Homepage, Yahoo Sports, Yahoo Finance, Yahoo News and AOL. This team is uniquely positioned to identify growth and revenue generation opportunities, design and implement solutions across consumer products and advertising platforms including video, display, native, and search.

A Lot About You:
As part of the Consumer Monetization Platform Engineering team, you will further accelerate our monetization capabilities and advance Yahoo's Signal Sphere and walled garden strategy, you will drive cutting-edge predictive modeling, audience segmentation, and real-time decisioning to enhance ad targeting and revenue outcomes.

Our Big Data footprints are among the largest few in the world, at double-digit petabyte scale. Developing this infrastructure presents many technical challenges in the areas of efficient query processing, large-scale stream processing, machine learning and modeling, as well as satisfying complex business rules.

If you are someone who is passionate about harnessing data at insane scale, enjoys working with new technologies, implementing new machine learning solutions and metrics systems, we want to hear from you!

Your Day:

• Work closely with data engineers, product managers, and sales teams to align data science initiatives with business goals.

• Design, train, and deploy machine learning models for audience segmentation and ad targeting.

• Analyze and interpret large-scale datasets to extract meaningful insights for monetization strategies.

• Develop and optimize real-time ML inference pipelines for ad decisioning.

• Experiment with different modeling techniques, A/B tests, and reinforcement learning strategies to improve performance.

• Collaborate with privacy and legal teams to ensure compliance with data regulations while maximizing model effectiveness.

• Collaborate with advertisers to understand precise targeting goals and campaign objectives

• Analyze multi-dimensional customer data to identify meaningful segmentation variables

• Design and develop sophisticated audience segmentation models using machine learning and statistical techniques

• Engineer customer features that capture nuanced behavioral and demographic characteristics

• Transform complex audience requirements into implementable segment definition logic

• Validate segment performance through rigorous statistical testing and metric analysis

• Continuously refine segmentation strategies to improve targeting precision

• Present findings, insights, and model performance improvements to leadership and stakeholders.

Qualifications:

• PhD or Master’s degree in Computer Science, Machine Learning, Statistics, or related fields; Or, equivalent experience

• 5+ years of experience in machine learning, data science, and predictive modeling, particularly in ad tech, audience segmentation, and bidding optimization.

• Strong proficiency in Python, Scala, or R, along with ML libraries such as TensorFlow, PyTorch, or Scikit-learn.

• Expertise in big data processing with Spark, Hadoop, or similar technologies.

• Experience with real-time ML models and inference pipelines for ad targeting.

• Deep understanding of auction dynamics, programmatic advertising, and bid landscape modeling.

• Strong knowledge of privacy-preserving ML techniques such as federated learning and differential privacy.

• Ability to translate business objectives into scalable dat