Sr Software Engineer - AI and Observability

Job Posting

Title:

Sr Software Engineer - AI and Observability

Disney Entertainment and ESPN Product & Technology is a global organization of engineers, product developers, designers, technologists, data scientists, and more – all working to build and advance the technological backbone for Disney’s media business globally. The team marries technology with creativity to build world-class products, enhance storytelling, and drive velocity, innovation, and scalability for our businesses. We are Storytellers and Innovators.

Creators and Builders. Entertainers and Engineers. We work with every part of The Walt Disney Company’s media portfolio to advance the technological foundation and consumer media touch points serving millions of people around the world.

As a Senior Software Engineer (P3), you will lead the design and implementation of intelligent, AI-driven systems that safeguard the reliability and performance of Disney’s global streaming ecosystem. You will be a technical leader in developing agentic systems, complex machine learning models, and high-throughput real-time pipelines that transform massive telemetry and log datasets into automated detection, root cause analysis, and proactive insights.

In this role, you will own the architectural vision for autonomous agents capable of reasoning over complex system behaviors across Disney+, Hulu, and ESPN. You will act as a bridge between engineering, product, and platform teams, translating high-level business needs into scalable AI solutions that reduce operational overhead. As a P3 engineer, you are expected to deliver mission‑critical features, mentor junior engineers, and drive engineering excellence through rigorous design reviews and high‑quality, production‑ready code in a fast‑paced, AI‑native environment.

• Own the design and operation of production‑grade, intelligent systems leveraging real‑time signals and AI‑driven detection to ensure the health of critical services and premium customer experiences.
• Lead the development of agentic AI systems powered by modern foundation models (e.g., Claude Opus/Sonnet, GPT‑4). Define the strategy for automated reasoning, decisioning, and predictive modeling for global‑scale system reliability.
• Oversee the creation of end‑to‑end data pipelines that process high‑volume telemetry and user signals into actionable, automated insights and root cause analysis.
• Design and maintain scalable APIs and microservices that provide explainability and predictive signals to cross‑functional engineering and product stakeholders.
• Partner with leadership and cross‑functional teams to embed intelligence into global workflows (incident response, release validation), significantly reducing Time‑to‑Detect (TTD) and Time‑to‑Resolve (TTR).
• Promote engineering best practices, provide technical guidance through code and design reviews, and drive innovation in observability and developer productivity through applied AI.

• 5+ years of applicable experience in backend development, with a proven track record of building and scaling AI‑powered or data‑driven applications.
• Advanced proficiency with modern models (GPT‑4/o1, Claude Opus/Sonnet, Bedrock), including deep experience in prompt engineering, model evaluation, and building complex agentic workflows using frameworks like Lang Chain or Lang Graph.
• Minimum 3 years of hands‑on experience deploying and monitoring ML systems (PyTorch/Tensor Flow) and large‑scale data processing (PySpark, Pandas) in production environments.
• Strong experience with AWS ecosystem and containerization (Docker, Kubernetes) at scale.
• Proven ability to lead technical projects, mentor junior talent, and champion software development best practices (Git, CI/CD, Agile).
• Expert level use of AI‑assisted development tools (e.g., Cursor, Claude) to accelerate team velocity and maintain high code quality.
• Exceptional communication skills with the ability to navigate ambiguity and explain complex AI/technical concepts to both technical and non‑technical partners.

• Experience implementing observability and monitoring systems for high‑volume, low‑latency…