The role

We are seeking a highly skilled and experienced Lead Machine Learning Engineer to drive the development and optimization of cutting-edge ML models in an ultra-low latency search ads ecosystem. In this role, you will partner closely with engineering, product, business stakeholders, and data science teams to ensure our ad serving platform delivers on core business goals: yield optimization, accurate prediction models, and scaled performance improvements. You will own key ML initiatives from concept to production, guiding a team of engineers and delivering robust solutions that enhance advertiser ROI, improve CTR predictions, streamline bidding strategies, and expand product search relevance.

As the Lead Machine Learning Engineer, you will leverage advanced ML techniques—from CTR prediction and yield optimization to advertiser bidding strategies and search relevance enhancements. You will also bring deep expertise in MLOps, data pipelines, and online experimentation frameworks. This is an exciting opportunity to shape the ML roadmap, influence strategic decisions, and contribute directly to business outcomes in a dynamic and fast-paced environment.

Responsibilities

• Define and champion the ML vision and strategy in collaboration with product and business stakeholders. Translate organizational objectives into well-scoped, impactful ML projects that optimize yield, CTR predictions, and advertiser bidding.
• Design, build, and refine ML models for key use cases: Yield Optimization & CTR Prediction, Advertiser Bidding & Pricing Models, Search Relevance and Personalization.
• Establish robust frameworks for A/B testing and synthetic experiments. Create and implement procedures and tools to track and evaluate the performance and accuracy of models and data. Continuously refine models based on real-world feedback and empirical evidence.
• Implement and maintain end-to-end ML pipelines, including data ingestion, feature engineering, model training, and deployment. Set up monitoring and alerting to track model stability, identify performance regressions, and ensure alignment with business KPIs over time.
• Work closely with pricing, engineering, product, and data science teams. Align ML initiatives with business strategies, guide key architectural decisions, and represent the ML team’s work to leadership.
• Provide technical guidance and mentorship to engineers on the ML team. Promote a culture of excellence, encourage innovation, and support career growth within the team.

Basic Qualifications

• A PhD or an MS with 8+ years of experience in a quantitative field (e.g., Computer Science, Statistics, Operations Research, or related) or equivalent industry experience in large-scale ML projects.
• Proven track record of building production ML models in one or more domains: ranking and relevance, CTR/CVR prediction, recommendation systems, or search.
• Expertise in statistical learning, machine learning, deep learning, and related methodologies.
• Experience developing low-latency, high-throughput online ML services and feature engineering pipelines at scale.
• Strong proficiency in Python or Java and familiarity with ML frameworks (e.g., TensorFlow, PyTorch, scikit-learn) and distributed data processing (e.g., Spark, Hadoop).
• Hands-on experience with MLOps, containerization, orchestration tools, and model monitoring in production environments.
• Demonstrated ability to translate cutting-edge research into pragmatic, high-quality production code.
• Excellent communication and interpersonal skills, with a proven ability to collaborate and influence cross-functional teams.
• Experience mentoring junior engineers and shaping technical best practices.

Preferred Qualifications

• 10+ years of experience building ML models in the ads domain, including yield optimization, keyword-level bidding, and search relevance.
• Experience implementing CTR/CVR prediction models and Learning-to-Rank algorithms at scale.
• Familiarity with reinforcement learning or contextual bandits for ad selection and exploration.
• Experience implementing and managing online experimentation frameworks to evaluate model performance (A/B tests, synthetic experiments).
• A demonstrated ability to incorporate first-party data signals, handle limited engagement data scenarios, and optimize models under shifting market conditions (promotions, holidays, varying budgets).

*Compensation Range: $200,000 - $240,000 

#LI-Onsite