Senior/Machine Learning Engineer — Performance Optimization

Role: Hybrid in Redwood City, CA. 

Must have: 3+ years of solid experience building machine learning, data science, ranking, prediction, recommendation, optimization, or large-scale data systems

PubMatic is the leading AI-powered ad tech company delivering measurable advertising performance through an intelligent, unified platform that connects buyers, publishers, data partners, and commerce media across CTV, mobile app, and omnichannel environments.

About the Role:

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. 

What You'll Do:

• 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

We’d Love for You to Have

•  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.

• 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.

Additional Information

Return to Office: PubMatic employees throughout the globe have returned to our offices via a hybrid work schedule (3 days “in office” and 2 days “working remotely”) that is intended to maximize collaboration, innovation, and productivity among teams and across functions.

Benefits: Our benefits package includes the best of what leading organizations provide such as, paid leave programs, paid holidays, healthcare, dental and vision insurance, disability and life insurance, commuter benefits, physical and financial wellness programs, unlimited DTO in the US (that we actually require you to use!), reimbursement for mobile and fully stocked pantries plus in-office catered lunches 5 days per week.

Diversity and Inclusion: PubMatic is proud to be an equal opportunity employer; we don’t just value diversity, we promote and celebrate it. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status

About PubMatic

PubMatic is one of the world’s leading scaled digital advertising platforms, offering more transparent advertising solutions to publishers, media buyers, commerce companies and data owners, allowing them to harness the power and potential of the open internet to drive better business outcomes. Founded in 2006 with the vision that data-driven decisioning would be the future of digital advertising, we enable content creators to run a more profitable advertising business, which in turn allows them to invest back into the multi-screen and multi-format content that consumers demand.

#LI-HYBRID