Lead Machine Learning Engineer

$172,300 - $231,100/Yr

Unclassified - Atlanta, GA

Full-time

Atlanta, GA

About the position

At Disney Entertainment & ESPN Technology, we are dedicated to reimagining the way audiences experience the world's most beloved stories. Our mission is to transform Disney's media business for the future by evolving our streaming and digital products, enhancing advertising and distribution capabilities, and delivering unmatched entertainment and sports content. As part of our team, you will play a crucial role in developing and maintaining recommendation and personalization algorithms for Disney Streaming's suite of applications, including Disney+ and Hulu. This position is an Individual Contributor role focused on content recommendations, where you will collaborate with Engineering, Product, and Data teams to apply machine learning methods to achieve strategic product personalization goals. In this role, you will lead the research, development, implementation, and optimization of recommendation and personalization algorithms. You will coordinate requirements and manage stakeholder expectations with Product, Engineering, and Editorial teams, ensuring that we meet key performance indicators (KPIs) for product areas. You will also be responsible for setting and meeting deadlines for both external and internal tools, such as offline evaluation tools for pre-production algorithms. As an Individual Contributor, you will help shape the roadmap for algorithmic work, addressing product requests for new recommendation features while driving larger company objectives in personalization and content recommendation. Your responsibilities will include utilizing cutting-edge machine learning methods to develop and implement algorithms for personalization and recommendation systems, maintaining deployed algorithms, and explaining methodologies to both technical and non-technical teams. You will also develop and maintain ETL pipelines using orchestration tools like Airflow and Jenkins, deploy scalable streaming and batch data pipelines to support petabyte-scale datasets, and establish best practices for algorithm development, testing, and deployment. Collaboration with product and business stakeholders will be essential to identify and define new personalization opportunities, improve data collection, experimentation, and analysis processes, and execute effective solutions for machine learning problems.

Responsibilities

• Utilize cutting-edge machine learning methods to develop and implement algorithms for personalization and recommendation systems.
• Maintain algorithms deployed to production and explain methodologies to technical and non-technical teams.
• Develop and maintain ETL pipelines using orchestration tools such as Airflow and Jenkins.
• Deploy scalable streaming and batch data pipelines to support petabyte-scale datasets.
• Establish and maintain algorithm development, testing, and deployment standards.
• Collaborate with product and business stakeholders to identify and define new personalization opportunities.
• Work with other data teams to improve data collection, experimentation, and analysis processes.
• Gauge the complexity of machine learning problems and execute simple approaches for quick, effective solutions.

Requirements

• Bachelor's degree in Computer Science, Information Systems, Software, Electrical or Electronics Engineering, or a comparable field of study, and/or equivalent work experience.
• 7+ years of experience developing machine learning models, performing large-scale data analysis, and/or data engineering experience.
• 5+ years writing production-level, scalable code (e.g. Python, Scala).
• 5+ years of experience developing algorithms for deployment to production systems.
• In-depth understanding of modern machine learning (e.g. deep learning methods), models, and their mathematical underpinnings.
• Experience deploying and maintaining pipelines (AWS, Docker, Airflow) and engineering big-data solutions using technologies like Databricks, S3, and Spark.
• Experience building and deploying full stack ML pipelines: data extraction, data mining, model training, feature development, testing, and deployment.

Nice-to-haves

• MS or PhD in statistics, math, computer science, or related quantitative field.
• Production experience with developing content recommendation algorithms at scale and familiarity with metadata management, data lineage, and principles of data governance.
• Experience loading and querying cloud-hosted databases.
• Building streaming data pipelines using Kafka, Spark, or Flink.

Benefits

• Medical, financial, and other benefits depending on the level and position offered.
• Bonus and/or long-term incentive units may be provided as part of the compensation package.