Machine Learning Engineer 5 - Decisioning & Optimization
Core
Building and operating end-to-end ML model serving infrastructure for real-time ad decisioning, scaling inference paths to support dozens of concurrent models at 1M+ QPS with strict latency budgets.
Role type
Senior IC machine learning infrastructure engineer (real-time ad decisioning)
Builds
Real-time model serving systems, feature hydration pipelines, and simulation infrastructure for ad marketplace optimization
Domain
Advertising technology / Real-time decisioning systems
Deliverable
production ML models
Required skills
Real-time model serving, high-throughput inference (1M+ QPS), sub-20ms latency optimization, feature engineering pipelines (online/offline consistency), model monitoring (drift detection, calibration), Java/Python/Scala, multi-threading, memory management, canary/shadow rollout, model versioning
Preferred skills
Ads domain (ranking, bid scoring, yield optimization), auction mechanics, budget pacing systems, simulation/counterfactual testing platforms, A/B testing infrastructure, CTV constraints, JVM ecosystem
Technologies
Java, Python, Scala, Chronon, Signal Service
Responsibilities
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 on every ad request; Design and optimize the feature serving path; Productionize scoring and ranking models for multi-stage ad selection; Build model performance monitoring in production; Build simulation infrastructure to replay production traffic against candidate models offline; Drive operational excellence for ML systems
Seniority
Senior, hands-on IC
