Machine Learning Engineer 5 - Ads Platform Engineering

Netflix is hiring machine learning engineers for its Ads Platform Engineering teams. The teams build the advertising systems and integrations that deliver ads across Netflix, using a mix of client and server side ad insertion, content delivery, ad encoding, and content understanding. This is a role for engineers who have worked in advertising and want to build real-time ad systems at scale.

Netflix launched its ad-supported tier in November 2022 to offer members a lower price point and give advertisers a way to reach engaged audiences. The teams are new and building quickly in the Connected TV advertising space.

What you will do

You will be assessed for one of several teams as you move through the interview process:

• Ads Inventory Management & Forecasting: build real-time inventory forecasting using ML models and ad server simulations, plus systems for publisher inventory management such as dynamic pricing, rate card management, product packaging, inventory split, and yield optimization.
• Core Ads Serving: power real-time ad decisioning with low-latency ML models, and manage budgeting, pacing algorithms, and dynamic allocation across direct and programmatic. The team also builds models for goal-based delivery optimization including CPC, CPV, and CPCV.
• Ads Programmatic: build interfaces with selected SSPs and DSPs to integrate with advertisers' buying mechanisms.
• Ads Member Experience: build and serve ad formats on the platform and own the integration between Netflix clients (TV, mobile app, web) and the ads serving infrastructure.
• Ads Identity & Audience: use ML models for identity resolution and behavioral and contextual audience targeting, while upholding member privacy.

Across these teams you would collaborate with science, product, engineering, operations, design, and consumer research stakeholders to deploy models at scale.

What they are looking for

• Proficiency in Java, C++, Python, or Scala, with an understanding of multi-threading and memory management.
• Experience building end-to-end ML model deployment and inference infrastructure for low-latency real-time ad systems.
• Experience handling very large data volumes with big data tools like Spark.
• Yield optimization, scoring, and bid ranking models, and dynamic allocation of direct, programmatic guaranteed, and non-guaranteed inventory.
• Modeling and building Cost Per Click, Cost Per View, and Cost Per Video Complete optimization.
• Productionized predictive models forecasting campaign effectiveness, including impressions, reach, clicks, conversions, and ROI.
• Building scalable simulation to model inventory scenarios such as demand fluctuations, pricing strategies, and inventory allocation.
• A general understanding of the advertising marketplace, with a focus on publisher-side challenges like fill rates and revenue in inventory management.

Nice to haves

• Experience productionizing ML models and deploying them at scale.
• Contributing to an ads industry technology standard such as VAST or OpenRTB, or work on an industry consortium or working group.
• Familiarity with publisher-side ad tech systems including ad servers, bidders, yield optimizers, and their demand-side counterparts (SSPs/DSPs).
• A good understanding of Lucene index and experience building one with large data volumes.
• Familiarity with legal compliance and ads regulations around the world.
• Experience in the CTV space and knowledge of its constraints.

Pay and benefits

Compensation is an annual salary only, with no bonuses. You choose each year how much of your compensation you want in salary versus stock options. The range for this role is $466,000.00 to $750,000.00. Netflix offers Health Plans, Mental Health support, a 401(k) Retirement Plan with employer match, a Stock Option Program, Disability Programs, Health Savings and Flexible Spending Accounts, Family-forming benefits, and Life and Serious Injury Benefits, plus paid leave of absence programs. Full-time salaried employees are immediately entitled to flexible time off.

This is a United States role. The job is open for no less than 7 days and will be removed when the position is filled.