Wayfair
Senior Machine Learning Scientist
Wayfair, Boston, Massachusetts, us, 02298
Who we are
The Bidding and Decisioning team under Wayfair Marketing Science is responsible for developing and managing machine learning models and strategies to optimize marketing decisions across paid media channels. We aim to create a leading, customer-focused, ML-powered decision engine that uses extensive first- and third-party data, in collaboration with engineering teams, to optimize every aspect of our marketing. This includes spend management, content optimization, segmentation, and campaign structures across major digital ad platforms like Google, Meta, Pinterest, and Microsoft Bing. Our work impacts hundreds of millions in ad spend, ensuring we provide the right marketing experience for each customer, at the right time, and at the right price throughout their buying journey.
What you’ll do
Identify new opportunities and evolve the spend management optimization framework, expanding its coverage for new use cases.
Build and implement ML solutions to enhance efficiency, defining problem statements, and delivering against technical and research objectives in a timely manner.
Collaborate cross-functionally with Marketing, MarTech (Product & Engineering), and ML Platform teams to align roadmaps, adopt best practices, and build scalable, sustainable bidding solutions.
Engage with external vendors, including Google, Meta, and Pinterest, to understand technical capabilities, inform bidding solution decisions, and influence strategic roadmaps.
Collaborate closely with engineering, infrastructure, and ML platform teams to adopt best practices for building and deploying scalable ML services.
Foster the development of junior ML scientists on the team through mentorship, knowledge-sharing, and support for subject matter expertise initiatives such as code reviews.
Who you are
Bachelor's or advanced degree (Master’s, PhD) in Computer Science, Economics, Mathematics, Statistics, or related field.
3-6 years of experience as an ML engineer, applied scientist, or research scientist, with a proven track record of delivering ML projects autonomously and driving measurable business impact, particularly in digital marketing decisioning (e.g., spend management, content optimization, segmentation) and/or ML decisioning systems.
Experience with end-to-end project ownership, including collaboration with business partners and strong written and verbal communication skills.
Strong SQL skills and excellent software engineering skills in Python.
Experience deploying machine learning models in production environments, with a focus on cloud-based solutions such as GCP (BigQuery, GCS, Vertex AI, Composer), as well as workflow orchestration tools like Airflow, model tracking using MLflow, and containerization technologies like Docker.
Nice to have
PhD in Computer Science, Economics, Mathematics, Statistics, or related field.
Expertise in causal inference, multi-armed bandits (MAB), reinforcement learning, control systems, and heterogeneous treatment effect estimation.
Strong background in statistical analysis, hypothesis testing, A/B testing methodologies, and quasi-experimental measurement methods.
Experience with specific marketing platforms: familiarity with Google Ads, Meta Ads, or other major advertising platforms is a definite advantage.
#J-18808-Ljbffr
The Bidding and Decisioning team under Wayfair Marketing Science is responsible for developing and managing machine learning models and strategies to optimize marketing decisions across paid media channels. We aim to create a leading, customer-focused, ML-powered decision engine that uses extensive first- and third-party data, in collaboration with engineering teams, to optimize every aspect of our marketing. This includes spend management, content optimization, segmentation, and campaign structures across major digital ad platforms like Google, Meta, Pinterest, and Microsoft Bing. Our work impacts hundreds of millions in ad spend, ensuring we provide the right marketing experience for each customer, at the right time, and at the right price throughout their buying journey.
What you’ll do
Identify new opportunities and evolve the spend management optimization framework, expanding its coverage for new use cases.
Build and implement ML solutions to enhance efficiency, defining problem statements, and delivering against technical and research objectives in a timely manner.
Collaborate cross-functionally with Marketing, MarTech (Product & Engineering), and ML Platform teams to align roadmaps, adopt best practices, and build scalable, sustainable bidding solutions.
Engage with external vendors, including Google, Meta, and Pinterest, to understand technical capabilities, inform bidding solution decisions, and influence strategic roadmaps.
Collaborate closely with engineering, infrastructure, and ML platform teams to adopt best practices for building and deploying scalable ML services.
Foster the development of junior ML scientists on the team through mentorship, knowledge-sharing, and support for subject matter expertise initiatives such as code reviews.
Who you are
Bachelor's or advanced degree (Master’s, PhD) in Computer Science, Economics, Mathematics, Statistics, or related field.
3-6 years of experience as an ML engineer, applied scientist, or research scientist, with a proven track record of delivering ML projects autonomously and driving measurable business impact, particularly in digital marketing decisioning (e.g., spend management, content optimization, segmentation) and/or ML decisioning systems.
Experience with end-to-end project ownership, including collaboration with business partners and strong written and verbal communication skills.
Strong SQL skills and excellent software engineering skills in Python.
Experience deploying machine learning models in production environments, with a focus on cloud-based solutions such as GCP (BigQuery, GCS, Vertex AI, Composer), as well as workflow orchestration tools like Airflow, model tracking using MLflow, and containerization technologies like Docker.
Nice to have
PhD in Computer Science, Economics, Mathematics, Statistics, or related field.
Expertise in causal inference, multi-armed bandits (MAB), reinforcement learning, control systems, and heterogeneous treatment effect estimation.
Strong background in statistical analysis, hypothesis testing, A/B testing methodologies, and quasi-experimental measurement methods.
Experience with specific marketing platforms: familiarity with Google Ads, Meta Ads, or other major advertising platforms is a definite advantage.
#J-18808-Ljbffr