Distributed Systems Engineer 5 - Decisioning & Optimization

Netflix•Los Angeles, CA

About The Position

At Netflix, our mission is to entertain the world. Together, we are writing the next episode - pushing the boundaries of storytelling, global fandom and making the unimaginable a reality. We are a dream team obsessed with the uncomfortable excitement of discovering what happens when you merge creativity, intuition and cutting-edge technology. Come be a part of what’s next. We launched a new ad-supported tier in November 2022 and are building an in-house world-class ad tech ecosystem to offer our members more choices in consuming their content. Our new tier allows us to attract new members at a lower price point while also creating a compelling path for advertisers to reach deeply engaged audiences. Our Team The Decisioning & Optimization engineering team sits within the Ad Serving & Decisioning org at Netflix Ads. We own the systems that power real-time ad decisioning, delivering relevant, high-quality ads while balancing revenue goals, advertiser outcomes, and member experience. Our work spans ML model serving infrastructure, ranking and scoring, auction mechanics, budget and pacing systems, and goal-based delivery optimization along with podding, traffic shaping models, and more. We are looking for a strong systems engineer to build and scale the core infrastructure behind ads optimization at Netflix. You will work across the stack from model serving to auction execution to pacing, shipping production systems that directly impact revenue and advertiser outcomes.

Requirements

7+ years building distributed systems and backend services at scale
Ads domain experience (2+ years): worked on ad serving, delivery, or marketplace systems
Experience with ML model serving infrastructure: real-time inference, model deployment pipelines, feature hydration, fallback strategies
Built or worked on core ad tech systems: ad servers, bidders, pacers, or ranking and scoring components
Built APIs and backend services that integrate across a multi-team platform
Understanding of ad serving concepts: inventory management, frequency capping, member ad experience quality, and supply-demand dynamics
Comfortable working at the intersection of engineering and data science, productionizing ML models into low-latency serving paths
Ability to operate in an environment that is a mix of big-tech scale and startup speed

Nice To Haves

Experience with auction mechanics: first-price, second-price, reserve pricing, bid shading
Experience building multi-stage ranking systems (retrieval, scoring, reranking), podding and ad break planning
Built or improved budget pacing and delivery control systems
Familiar with CTV constraints: server-side ad insertion, live event ad serving at scale
Experience with experimentation infrastructure: A/B testing, holdout groups, marketplace experiments
Built simulation or counterfactual testing platforms for marketplace or auction systems

Responsibilities

Build and evolve the real-time ad decisioning path: ranking, scoring, bidding, and pacing under strict latency and throughput constraints
Develop and operate ML model serving infrastructure supporting dozens of concurrent hot-path models with sub-20ms P99 inference, including model routing, lifecycle management, fallback tiers, and calibration serving
Partner with Science and Platform teams to productionize models and deploy algorithms into the serving stack
Build simulation and testing frameworks to enable offline validation of marketplace changes before live rollout
Implement and improve real-time pacing systems that drive budget delivery accuracy across campaign lifetimes
Contribute to goal-based delivery optimization: dynamic allocation of budget and inventory across demand channels
Build reusable components and clean interfaces that improve developer velocity across the team
Participate in operational excellence: reliability, observability, deployment automation, and incident response across the optimization stack