ML & Observability Engineer: Real-Time Anomaly Detection

Disney Cruise Line - The Walt Disney Company; Glendale (CA); On-site; Confidential; Full time

Job summary

Disney Glendale, CA seeks a Software Engineer II to build and operate ML-powered systems that enhance the reliability of Disney's streaming ecosystem. You will work on production ML models—autoencoders for anomaly detection and LLM-powered gates—transforming telemetry into automated insights across Disney+.

Hulu, and ESPN. You will collaborate with engineering teams to embed intelligence into operational workflows, deliver end-to-end features, and participate in model design, training, and

Qualifications

• 3+ years of professional software engineering experience building ML-powered backends and RESTful APIs.

Responsibilities

• Contribute to production ML models for anomaly detection, including autoencoders and statistical threshold models.
• Develop and improve ML training pipelines on GPU clusters using PyTorch.
• Engineer features from time-series telemetry and implement data quality safeguards for model consumption.
• Support real-time ML inference systems including model serving, detection logic, and alerting.
• Build AI-driven capabilities using foundation models for automated investigation over system health signals.
• Create and deploy scalable APIs and services (FastAPI) delivering ML predictions and insights.
• Partner cross-functionally to embed ML intelligence into incident response and release validation.
• Contribute to model improvement via evaluation, retraining, and threshold tuning.

Skills

Python programming

ML engineering

Analytical thinking

Collaboration

Communication

Education

Bachelor’s degree in Computer Science or related field

Tools

PyTorch

TensorFlow

MLflow

Weights & Biases

FastAPI

Docker

AWS

PySpark

Job description

Disney Glendale, CA seeks a Software Engineer II to build and operate ML-powered systems that enhance the reliability of Disney's streaming ecosystem. You will work on production ML models—autoencoders for anomaly detection and LLM-powered gates—transforming telemetry into automated insights across Disney+.

Hulu, and ESPN. You will collaborate with engineering teams to embed intelligence into operational workflows, deliver end-to-end features, and participate in model design, training, and