Principal Applied Machine Learning Engineer (Personalization)

Company: Disney Media & Entertainment Distribution
Location: San Francisco
Posted on: August 7, 2022

Job Description:

Applied Machine Learning Engineers and Data Scientists on the Disney Streaming Machine Learning and Innovation team develop and maintain recommendation and personalization algorithms for Disney Streaming's suite of streaming video apps, notably Disney+ and Hulu. As a member of this team you will collaborate across Engineering, Product, and Data teams to apply machine learning methods to meet strategic product personalization goals, explore innovative, cutting edge techniques that can be applied to recommendations, and constantly seek ways to optimize operational processes.

This is an Individual Contributor leadership role in content recommendations. You will be expected to lead recommendation and personalization algorithm research, development, and optimization for particular product areas, and to coordinate requirements and manage stakeholder expectations with Product, Engineering, and Editorial teams. You will be expected to help meet KPIs for product areas and to set and meet deadlines for external and internally facing tools, such as offline evaluation tools for pre-production algorithms. As an IC leader, you will also be responsible for helping to set the roadmap for algorithmic work - not only for how to approach product requests for new recommendation features, but for helping to drive larger company objectives in the areas of personalization and content recommendation.

--- Algorithm development and maintenance: Utilize cutting edge machine learning methods to develop algorithms for personalization, recommendation, and other predictive systems; maintain algorithms deployed to production and be the point person in explaining methodologies to technical and non-technical teams
--- Analysis and Algorithm Optimization: Perform deep dive analysis on app interactions and user profiles as they relate to algorithm output in order to drive improvements in key personalization metrics
--- MVP development: Develop innovative machine learning products to be used for new production features or downstream by production algorithms
--- Development Best Practices: Maintain existing and establish new algorithm development, testing, and deployment standards
--- Collaborate with product and business stakeholders: Identify and define new personalization opportunities and work with other data teams to improve how we do data collection, experimentation and analysis

Required Qualifications:

--- 10+ years of analytical experience
--- 8+ years of experience developing machine learning models and performing data analysis with Python or R
--- 8+ years writing production-level, scalable code (e.g. Python, Scala)
--- Bachelor's degree in statistics, math, computer science, or related quantitative field
--- Experience developing algorithms for deployment to production systems
--- Experience working cross functionally with technical and non-technical teams to solve complex problems
--- In-depth understanding of modern machine learning (e.g. deep learning methods), models, and their mathematical underpinnings
--- Experience with cloud services in a production environment (particularly AWS)
--- Familiarity with data exploration and data visualization tools like Tableau, Looker, Chartio, etc.
--- Understanding of statistical concepts (e.g., hypothesis testing, regression analysis)
--- Ability to gauge the complexity of machine learning problems and a willingness to execute simple approaches for quick, effective solutions as appropriate
--- Strong written and verbal communication skills
--- Ability to explain how models are used and algorithms behave to both technical and non-technical audiences

Preferred Qualifications:

--- MS or PhD in statistics, math, computer science, or related quantitative field
--- Production experience with developing content recommendation algorithms at scale
--- Production experience with graph based models (e.g. node2vec)
--- Experience building and deploying full stack ML pipelines: data extraction, data mining, model training, feature development, testing, and deployment
--- Experience with graph-based data workflows such as Apache Airflow
--- Experience engineering big-data solutions using technologies like EMR, S3, Spark, Databricks
--- Familiar with metadata management, data lineage, and principles of data governance
--- Experience loading and querying cloud-hosted databases such as Snowflake
--- Building streaming data pipelines using Kafka, Spark, or Flink
--- Familiarity with automated deployment, AWS infrastructure, Docker or similar containers

Additional Information:

Location: New York, NY, San Francisco, CA or Seattle, WA preferred but also open to US Remote for the right candidate

#DisneyTech

Keywords: Disney Media & Entertainment Distribution, San Francisco , Principal Applied Machine Learning Engineer (Personalization), Engineering , San Francisco, California