Senior ML Engineer - Audience Enrichment

It takes powerful technology to connect our brands and partners with an audience of hundreds of millions of people. Whether you're looking to write mobile app code, engineer the servers behind our massive ad tech stacks, or develop algorithms to help us process trillions of data points a day, what you do here will have a huge impact on our business-and the world.

Our platform is the foundational identity and data layer for 900M+ monthly active users, serving 2.5B+ profiles at massive scale. We are building a predictive, identity-centric insights engine—ensuring our audience is understood with precision to deliver hyper-personalized experiences and advertising solutions across all our digital properties.

Our mission centers on first-party data strategy: capturing, enriching, and activating audience signals to build a 360-degree view of every user. We operate under a Privacy-by-Design philosophy, adhering to global regulations (GDPR, CCPA) and industry security standards, while leveraging a cloud-native stack across GCP (Big Query, Spanner, Dataflow, Composer, GKE) and AWS, with modern MLOps practices to deliver measurable business impact.

As a Senior ML Engineer, you will develop and optimize end-to-end machine learning solutions that transform raw user data into actionable audience intelligence. Your predictive models—including Lookalike audiences, Propensity scores, and Churn predictions—enable Product, Engineering, and Sales teams to deliver hyper-personalized experiences and maximize the commercial value of our 900M+ monthly active users.

You will build production ML pipelines processing data from our 2.5B+ profile platform, creating enrichment signals that directly impact user engagement, ad revenue, and retention. Your work requires balancing model accuracy, computational efficiency, and data privacy while operating at massive scale across petabyte-scale data infrastructure.

This role demands expertise in production ML engineering, large-scale data processing frameworks (Spark, Beam, Big Query), and MLOps practices. You will collaborate closely with Data Science, Product, and Engineering teams to translate business requirements into scalable ML solutions that drive measurable business outcomes.

• Develop and optimize end-to-end ML solutions for audience segmentation, predictive modeling, and behavioral enrichment at 2.5B+ profile scale
• Build reliable production pipelines for training, evaluating, and deploying ML models using GCP infrastructure (Vertex AI, Dataflow, Composer)
• Design robust feature engineering pipelines using large-scale data processing frameworks (Spark, Beam, Big Query)
• Implement comprehensive monitoring solutions tracking model performance, data drift, prediction quality, and business impact metrics
• Tune, validate, and optimize ML models for accuracy, efficiency, and scalability while managing computational costs
• Collaborate with Data Science teams to product ionize research models and translate prototypes into scalable production systems
• Partner with Product teams to understand business requirements and deliver ML capabilities for audience intelligence
• Apply ML engineering best practices including version control (Git), automated testing, CI/CD workflows, and model versioning
• Create comprehensive documentation for ML systems, feature pipelines, model artifacts, and operational runbooks
• Improve model efficiency, inference latency, and resource utilization for cost-effective production serving
• Troubleshoot data pipeline failures, model serving issues, and data quality problems in production environments
• Participate in technical discussions, code reviews, and knowledge sharing across teams

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Machine Learning, or related technical field

• 5+ years software engineering experience building production systems
• 3+ years in ML engineering, data science, or applied machine learning roles
• 2+ years implementing and deploying ML models to production environments at scale
• 2+ years hands‑on experience with GCP (Big Query, Dataproc, Composer,…