Machine Learning Engineer 5, Decisioning & Optimization

What you'll do

• Build and operate end-to-end ML model serving infrastructure for real-time ad decisioning.
• Scale inference paths to support dozens of concurrent models at 1M+ QPS with strict latency budgets.
• Design and optimize the feature serving path to ensure sub-10ms P99 fetch latency.
• Productionize scoring and ranking models for multi-stage ad selection and auction integration.
• Build production monitoring for inference latency, prediction distribution shifts, and feature drift.
• Develop simulation infrastructure to replay production traffic against candidate models for offline validation.
• Drive operational excellence for ML systems including reliability, capacity planning, and incident response.

What we're looking for

• 7+ years of software engineering experience.
• 3+ years of experience focused on ML infrastructure, model serving, or ML platform work in an ads or real-time decisioning 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, memory management, and performance optimization.
• Hands-on experience with ML serving frameworks, serialization, runtime optimization, and deployment constraints.
• Experience with feature engineering pipelines for real-time systems, including online/offline consistency and hydration strategies.
• Strong understanding of model monitoring in production, including drift detection, prediction distribution analysis, and latency profiling.
• Experience with ads domain, auction mechanics, or budget pacing and delivery control systems (preferred).