The Walt Disney Company

Principal Machine Learning Engineer - ESPN+ Personalization

The Walt Disney Company

full-time

Posted on:

Origin:  • 🇺🇸 United States • California, New York, Washington

Visit company website
✨ AI Apply
Manual Apply

Salary

💰 $202,900 - $297,900 per year

Job Level

Lead

Tech Stack

AWSAzureCloudGoogle Cloud PlatformPythonPyTorchTensorflow

About the role

  • Serve as the technical architect and primary owner for the design and implementation of ESPN’s real-time short-form video recommendation system
  • Design, develop, and deploy large-scale, end-to-end ML pipelines for real-time retrieval, ranking, and personalization at scale
  • Lead research, prototyping, and product ionization of cutting-edge recommendation algorithms, leveraging deep learning, embeddings, sequence models, transformers, and multi-task learning
  • Define system architecture for low-latency online inference, streaming data pipelines, feature stores, and online/offline model serving
  • Collaborate with cross-functional stakeholders to define personalization strategies, system requirements, metrics, and experimentation frameworks to drive continuous improvement
  • Lead complex technical discussions and make high-impact design decisions balancing model quality, scalability, system latency, and operational reliability
  • Establish ML engineering best practices, development standards, and model governance processes to ensure robust, reliable, and reproducible ML systems
  • Mentor and coach other machine learning engineers, helping to grow technical capability across the team and broader organization
  • Stay current with state-of-the-art research and industry trends; proactively incorporate emerging technologies into ESPN’s personalization roadmap

Requirements

  • Proven track record of designing and deploying real-time, large-scale ML recommendation systems (preferably in consumer or streaming platforms)
  • Strong expertise in machine learning algorithms, deep learning architectures (e.g., sequence models, transformers, embeddings, multi-task learning), and personalization methodologies
  • Deep understanding of real-time serving architectures, online inference, feature stores, streaming data pipelines, and low-latency ML systems
  • Proficiency in Python and common ML frameworks (e.g., TensorFlow, PyTorch, ONNX), and experience integrating ML models into production services
  • Demonstrated technical leadership in cross-functional projects; ability to independently own technical solution design, architecture, and execution in ambiguous 0→1 environments
  • Strong communication skills to collaborate with engineering, product, data, and business stakeholders
  • 8+ years of hands-on experience building and deploying machine learning models in production environments, with at least 2+ years in recommendation systems or personalization
  • Experience building short-form video or content-based recommendation systems, including ranking, retrieval, exploration/exploitation, and diversity modeling
  • Deep knowledge of real-time personalization challenges such as cold start, feedback loops, delayed labels, and temporal dynamics
  • Experience with experimentation platforms (e.g., A/B testing, bandits, reinforcement learning) to drive continuous optimization of recommendation systems
  • Experience designing ML systems on cloud platforms (AWS, GCP, Azure) with distributed compute, streaming data, and scalable online serving
  • Familiarity with retrieval models, approximate nearest neighbor search, graph-based recommenders, and large-scale embedding management
  • Experience collaborating with product and business stakeholders to define personalization goals, metrics, and KPIs
  • Strong mentoring capability to help grow and guide a new ML team; prior experience establishing technical standards, ML development best practices, and team capability building
  • Prior experience operating in a fast-paced startup or new product incubation environment