The role is for an ML engineer at Netflix, focusing on building and operating end-to-end ML model serving infrastructure for real-time ad decisioning. The Decisioning & Optimization engineering team is responsible for systems that determine ad impressions and campaign budgets. The position requires scaling inference paths and optimizing feature serving while ensuring low latency. The engineer will work closely with Data Science and Platform teams to drive operational excellence in ML systems.

• 7+ years of software engineering experience, with 3+ years focused on ML infrastructure or model serving in an ads context.
• Experience building and operating real-time model serving systems at high QPS with sub-20ms latency.
• Proficiency in Java, Python, or Scala with a solid understanding of multi-threading and performance optimization.
• Hands-on experience with ML serving frameworks and deployment constraints.
• Strong understanding of model monitoring in production, including drift detection and latency profiling.

• Build and operate end-to-end ML model serving infrastructure for real-time ad decisioning.
• Scale the inference path to support dozens of concurrent models at 1M+ QPS with strict latency budgets.
• Design and optimize the feature serving path for low fetch latency and consistency.
• Productionize scoring and ranking models for multi-stage ad selection and integrate model outputs into auction.
• Build model performance monitoring in production to detect issues before revenue impact.

• Employees at Netflix are often offered flexible, people-first benefits—unlimited time away, generous parental leave, global family-forming support, mental-health programs (mindfulness, free counseling/coaching), and health coverage tailored by country. Financially, Netflix pays at personal top-of-market and lets employees choose their mix of cash vs. fully-vested 10-year stock options, alongside donation and volunteer matching. Convenience perks can include trust-based travel/expense policies, relocation support, and “Work, Not Drive” rideshare flexibility.