Principal Software Engineer - Observability
Core
Design and build intelligent, production-grade observability systems using AI-driven detection and autonomous agentic workflows to ensure reliability and performance of Disney's large-scale streaming ecosystem.
Role type
Principal Software Engineer (AI-powered Observability)
Builds
Telemetry pipelines, dashboards, alerting systems, and autonomous agentic systems for system health monitoring.
Domain
Media Streaming / AI Engineering / Observability
Deliverable
production ML models | product features
Required skills
AI/ML engineering, autonomous agentic system design, model orchestration (LangChain/LangGraph), prompt engineering, API design, microservices architecture, cloud-native deployments, CI/CD, cost optimization for AI models
Preferred skills
Observability domain expertise (Datadog, Grafana, OpenTelemetry), enterprise AI services integration (AWS Bedrock), local open-source model deployment, large-scale data platforms
Technologies
Anthropic, OpenAI, Google, Meta, LangChain, LangGraph, FastAPI, Flask, AWS, Azure, GCP, EKS, Docker, GitHub, Cursor, Claude Code
Responsibilities
Design intelligent systems for real-time signal detection and root cause analysis; Build fully autonomous agentic systems with minimal human intervention; Develop multi-agent orchestration patterns and memory systems; Create end-to-end data and decisioning pipelines; Optimize AI usage costs through prompt and context management; Modernize unfamiliar codebases with AI to improve productivity.
Seniority
Principal, hands-on IC with technical leadership