Principal ML Scientist

Principal / Sr. Principal ML Scientist (Causal Inference, Reinforcement Learning, Ranking & Bid Optimization)

Role Overview

We are looking for a Principal / Sr. Principal Applied ML Scientist to lead the development of next-generation machine learning systems powering recommendations, search, ads ranking, and monetization platforms at scale. This is a high-impact Individual Contributor (IC) role requiring deep expertise in causal inference, unbiased learning systems, reinforcement learning, and large-scale optimization techniques that improve long-term user engagement, relevance, and business outcomes.

The ideal candidate will combine strong hands-on technical depth with cross-functional influence, driving architecture, research direction, and ML best practices across Ads, Recommendations & Personalization, and Search pods.

Key Responsibilities

• Lead the design and deployment of advanced ML systems for recommendations, search, and ads monetization at large scale.
• Drive research and productionization of applied causal inference techniques for ranking and recommendation systems, including:
• Unbiased Learning-to-Rank
• Counterfactual/offline evaluation
• Incrementality measurement
• Position bias estimation and mitigation
• Treatment effect modeling
• Build and optimize Reinforcement Learning (RL) frameworks for long-term optimization across user engagement, retention, and monetization objectives.
• Develop scalable solutions for Cold Start and Long Tail discovery problems using:
• Embedding-based retrieval systems
• Exploration/exploitation strategies
• Catalog-wide optimization
• Representation learning techniques
• Lead innovations in Ads Ranking and marketplace optimization, including:
• Bid optimization
• Auction-aware ML systems
• Budget pacing
• Attribution modeling
• Simulation frameworks
• Multi-objective optimization balancing revenue, relevance, user experience, and long-term value
• Architect robust experimentation and evaluation frameworks for measuring model impact reliably in dynamic environments.
• Act as a technical mentor and thought leader across Ads, Recommendations & Personalization, and Search pods by:
• Guiding senior engineers and scientists on ML architecture and experimentation
• Driving best practices for causal inference and evaluation
• Influencing roadmap and technical strategy across teams
• Contribute as a hands-on technical leader through model development, experimentation, system design, and productionization.

Preferred Qualifications

• 10+ years of experience in Machine Learning, Recommender Systems, Search, Ads, or Marketplace Optimization.
• Deep expertise in causal inference and counterfactual learning applied to large-scale recommendation/search/ads systems.
• Strong hands-on experience with Reinforcement Learning for production recommendation or monetization systems.
• Proven experience building large-scale ranking, retrieval, and personalization systems.
• Strong understanding of:
• Learning-to-Rank
• Bandits and exploration strategies
• Representation learning / embeddings
• Auction systems and ads marketplaces
• Multi-objective optimization
• Demonstrated ability to influence technical direction and drive execution in a highly cross-functional environment without direct people management responsibility.

Good to Have

• Experience building ML systems for Notifications, Engagement, or CRM platforms, including:
• Send-time optimization
• Cross-channel orchestration
• Personalized content optimization

What Makes This Role Exciting

• Opportunity to solve cutting-edge problems at the intersection of causal inference, RL, personalization, and marketplace optimization.
• Direct impact on large-scale user experience, discovery, engagement, and monetization systems.
• Ability to influence ML strategy and platform evolution across multiple high-impact domains.
• Work with high-scale, high-dimensional datasets and state-of-the-art ML infrastructure.