Operate production MLOps infrastructure for Walt Disney Animation Studios, focusing on secure AI deployments, model metrics, and service reliability.
In this senior engineering role, you will support AI-powered tools and machine learning infrastructure within production environments. Walt Disney Animation Studios’ SRE team builds performant infrastructure used daily by artists creating animated content. You will partner with stakeholders, develop operational standards, and improve visibility, diagnosis, and recovery across services.
Key Responsibilities:

Securely deploy and operate AI-powered production tools
Implement MLOps capabilities for validation, routing, and fallback
Create telemetry for model benchmarking and inference latency
Develop runbooks that reduce mean time to repair
Build internal tools for platform and application diagnosis
Requirements:

Five or more years in SRE, DevOps, or technical operations
Experience implementing enterprise MLOps infrastructure
Knowledge of AWS Bedrock, Artifactory, LiteLLM, or related tools
Experience with monitoring tools including Datadog, Prometheus, and Grafana
Programming proficiency in Python, Java, Scala, Go, Rust, or Ruby
Use MLOps, observability, secure deployment, and reliability engineering expertise across Walt Disney Animation Studios’ production platforms.

#J-18808-Ljbffr

Senior MLOps Site Reliability Engineer