Machine Learning Engineer 5 - Ads Platform Engineering
$466,000–$750,000 year
On-siteLos Gatos, California, United States
Job Summary
Build state-of-the-art real-time inventory forecasting solutions leveraging machine learning models and high-performance ad server simulations. Develop complex ML models for low-latency environments to power real-time ad decisioning, balancing revenue goals with advertiser outcomes through budgeting, pacing algorithms, and dynamic allocation. Engineer interfaces with selected SSPs and DSPs to integrate with advertiser buying mechanisms, while optimizing ad format integration across Netflix clients including TV, mobile, and web. Deploy productionized predictive models to forecast campaign effectiveness metrics such as impressions, reach, clicks, conversions, and ROI, ensuring brand safety and member experience integrity. Collaborate with cross-functional stakeholders from science, product, engineering, and consumer research to productionize and deploy models at scale within the rapidly growing connected TV advertising space.
Required Qualifications
- Proficiency in Java, C++, Python, or Scala with a solid understanding of multi-threading and memory management
- Experience in building end-to-end ML model deployment and inference infra for low-latency real-time ad systems
- Experience in handling data at extremely large volumes with big data tools like Spark
- Yield Optimization, scoring, and bid ranking models
- Dynamic Allocation of direct/programmatic guaranteed and non-guaranteed inventory
- Modeling and Building Cost Per Click, Cost Per View, and Cost Per Video Complete modeling and optimization
- Productionized predictive models to forecast the effectiveness of advertising campaigns, including metrics like impressions, reach, clicks, conversions, and ROI
- Building Scalable Simulation solution to model different inventory scenarios, including demand fluctuations, pricing strategies, and inventory allocation
- General understanding of the advertising marketplace and landscape, with a focus on publisher side challenges like optimizing fill rates and maximizing revenue in the context of inventory management
- Collaborate with cross-functional stakeholders from science team, product, engineering, operations, design, consumer research, etc., to productionize and deploy models at scale
Desired Qualifications
- Experience in productionizing ML models and deploying models at scale
- Contributed to an ads industry technology standard (e.g VAST, OpenRTB) or worked on an industry consortium effort, working group etc
- Familiar with publisher-side ad tech systems including ad servers, bidders, yield optimizers, and their demand-side counterparts (SSPs/DSPs)
- Good understanding of Lucene index and had experience building Lucene index with large volume of data
- Familiarity with legal compliance and changing landscape of ads regulations around the world
- Experience working in the CTV space and knowledge of its unique constraints
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.