Machine Learning Scientist III, Ads Optimization & Automation

**Salary Range:** $184,800 \- $196,350 per year. Individual compensation is determined by skills, qualifications, experience, and location. Compensation details listed in the posting reflect the annual base salary only and do not include equity. Who We Are Wayfair’s Advertising business is rapidly expanding, adding hundreds of millions of dollars in profits to Wayfair. We build Sponsored Products, Display \& Video Ad offerings that cater to a variety of Advertiser goals while showing highly relevant and engaging Ads to millions of customers. We are evolving our Ads Platform to empower advertisers across all sophistication levels to grow their business on Wayfair at a strong, positive ROI and are leveraging state of the art Machine Learning techniques. The Advertising Demand Science team is central to this effort. We leverage machine learning and generative AI to streamline campaign workflows, delivering impactful recommendations on budget allocation, target Return on Ad Spend (tROAS), and SKU selection. We explore the economics of our advertising system to understand impacts of advertisers’ changes to their outcomes. Additionally, we are developing intelligent systems for creative optimization and exploring agentic frameworks to further simplify and enhance advertiser interactions. We are looking for an experienced Machine Learning Scientist III to join the Advertising Demand Science team. In this role, you will be responsible for the development of intelligent agentic systems and other machine learning capabilities supporting our ads business. You will work closely with other scientists, as well as members of our internal Product and Engineering teams, to apply your engineering and machine learning skills to solve some of our most impactful and intellectually challenging problems to directly impact Wayfair’s revenue. What you’ll do \* Provide technical leadership in the development of agentic systems by advancing the state\-of\-the\-art in machine learning techniques to support recommendations for Ads campaigns and other optimizations. \* Design, build, deploy and refine extensible, reusable, large\-scale, and real\-world platforms that optimize our ads experience. \* Work cross\-functionally with commercial stakeholders to understand business problems or opportunities and develop appropriately scoped machine learning solutions \* Collaborate closely with various engineering, infrastructure, and machine learning platform teams to ensure adoption of best\-practices in how we build and deploy scalable machine learning services \* Identify new opportunities and insights from the data (where can the models be improved? What is the projected ROI of a proposed modification?) \* Research new developments in advertising, sort and recommendations research and open\-source packages, and incorporate them into our internal packages and systems. \* Be obsessed with the customer and maintain a customer\-centric lens in how we frame, approach, and ultimately solve every problem we work on. Who you are \* Minimum 2\+ years of experience with PhD, or 4\+ years of industry experience with MS, or 6\+ years of experience with a BS in a quantitative STEM field. \* 2\+ years of experience developing, evaluating, optimizing and deploying machine learning models, with a focus on advertising, bidding, recommendations, ranking, or personalization. \* Strong theoretical understanding of agentic systems and machine learning applied to large\-scale ML problems. \* Proficiency in Python and experience with ML frameworks such as TensorFlow, PyTorch, or Scikit\-Learn. \* Familiarity with data processing and ML pipeline orchestration (Airflow, Kubeflow, MLflow). \* Strong coding skills and familiarity with building scalable ML systems in cloud environments (AWS, GCP, Azure). \* Ability to work with others to help design experiments and analyze results using A/B testing and statistical techniques. \* Excellent communication skills, with the ability to explain complex ML concepts to non\-technical stakeholders and drive data\-driven decisions. Nice to have \* Familiarity with Machine Learning platforms offered by Google Cloud and how to implement them on a large scale (e.g. BigQuery, GCS, Dataproc, AI Notebooks). \* Experience in advertising \* Experience in Economics problems common in e\-commerce \* Hands\-on Agentic experience with chat\-based products deployed to consumers