Machine Learning Scientist 5, Forecasting Aggregation

What you'll do

• Build and iterate on supervised machine learning models to predict campaign delivery outcomes like reach and frequency.
• Replace the current rules-based simulation engine with fast, accurate, and learnable models.
• Design rigorous offline and online evaluation frameworks to measure model accuracy and robustness against seasonality.
• Own feature engineering and contribute to the team's feature store using ad-serving logs and campaign attributes.
• Ensure model outputs are explainable and interpretable for sales and media-planning stakeholders.
• Partner with ML engineers to deploy models at scale and monitor production health and drift.
• Communicate technical decisions and trade-offs clearly to both technical and non-technical audiences.

What we're looking for

• Advanced degree (PhD or Master's) in Statistics, Mathematics, Computer Science, or a related quantitative field.
• 5+ years of relevant experience building machine learning models on large-scale data.
• Deep expertise in supervised learning methods with a strong bias toward interpretable and explainable models.
• Strong feature engineering skills and familiarity with feature stores and standard ML lifecycle practices.
• Strong programming skills in Python and SQL.
• Working knowledge of ad-serving and campaign concepts, including delivery risk, targeting, and bidding.
• Ability to communicate technical and statistical concepts clearly to audiences at many levels.
• Experience at a DSP, SSP, or publisher-side ad platform (preferred).