Staff Machine Learning Engineer

Join Warner Bros. Discovery as a Staff Machine Learning Engineer to build and scale the production inference platform for the global streaming app Max. You will own the architecture and roadmap for a self-service inference platform on Kubernetes, ensuring low-latency, high-volume model serving for over 100 million users worldwide. This role offers the opportunity to drive engineering and operational excellence in a fast-paced environment, directly impacting the viewer experience.

• Own model serving runtime architecture and roadmap
• Lead large-scale production model migrations
• Build and maintain high-performance serving backends
• Design autoscaling and multi-region resilience
• Drive observability, cost optimization, and performance tuning
• Define ML lifecycle contract from training to production