Senior/Machine Learning Engineer — Performance Optimization

PubMatic•Redwood City, CA

5d•$260,000 - $330,000•Hybrid

About The Position

We are looking for a Machine Learning Engineer to help build and improve performance optimization models for PubMatic’s Activate platform. This role is focused on applying machine learning, data analysis, feature engineering, model training, experimentation, and production ML techniques to improve advertiser outcomes across performance advertising goals such as CTR, VCR, CPC, CPA, and ROAS. The ideal candidate has strong ML fundamentals, good engineering skills, and interest in building models that operate at large scale in real production systems.

Requirements

3+ years of experience building machine learning, data science, ranking, prediction, recommendation, optimization, or large-scale data systems.
Strong understanding of core ML concepts such as supervised learning, classification, regression, ranking, calibration, feature engineering, model evaluation, and experimentation.
Experience training, evaluating, and improving production-oriented ML models.
Experience working with large datasets using SQL, Spark, Python, or similar tools.
Strong programming skills in Python, Java, Scala, Go, C++, or similar languages.
Ability to reason about model quality, data quality, business impact, and production tradeoffs.
Comfort working with ambiguous data problems and iterating through analysis, modeling, experimentation, and production deployment.
BS or MS degree in Computer Science, Machine Learning, Statistics, Mathematics, Engineering, or a related technical field, or equivalent practical experience.

Nice To Haves

Experience in ads, search, recommendations, marketplaces, e-commerce, fintech, pricing, forecasting, bidding, or real-time optimization systems.
Experience with CTR/CVR prediction, conversion modeling, campaign optimization, bid optimization, forecasting, calibration, or user-value modeling.
Familiarity with programmatic advertising, ad serving, attribution, pacing, identity, performance advertising, or real-time bidding.
Experience with TensorFlow, PyTorch, XGBoost, LightGBM, Spark ML, or similar ML frameworks.
Experience with A/B testing, online experimentation, model monitoring, or production ML observability.
Experience working with sparse labels, delayed feedback, biased datasets, or noisy attribution.
Experience working cross-functionally with product, engineering, analytics, or business stakeholders.

Responsibilities

Build, train, evaluate, and improve machine learning models for prediction, ranking, campaign optimization, bidding, forecasting, and calibration.
Work with large-scale datasets from auctions, impressions, clicks, video events, conversions, users, context, inventory, campaigns, and marketplace feedback.
Develop and improve features, training datasets, labels, and evaluation workflows for performance advertising models.
Analyze model performance across offline metrics, online experiments, campaign outcomes, and business KPIs.
Help improve models for CTR, CVR, VCR, CPA, ROAS, app-install, user-value, and campaign-performance optimization.
Work with senior ML engineers to improve calibration, model monitoring, experimentation, and production feedback loops.
Debug model-quality issues related to feature quality, label quality, sparse conversions, attribution noise, delayed feedback, data freshness, or online/offline metric mismatch.
Collaborate with performance advertising signal engineers to use model-ready features, labels, attribution windows, and feedback loops effectively.
Partner with engineering teams to deploy models into production decisioning systems and monitor their impact.
Work cross-functionally with product, analytics, platform, and business teams to understand campaign performance problems and translate them into ML work.