Software Development Engineer - Machine Learning, Prime Video Recommendations

  • Amazon,
  • Seattle, WA
  • 3 hours ago
company banner
Full Time

Job Description


Job summary
Just finished Wheel of Time and want to watch more of the same? Looking for a movie that's like Tomorrow War? So are millions of our Prime Video customers. The Prime Video Relevance team suggests videos that are relevant and tailored to our customers' schedules and environments. We help our customers find content they didn't even known they were looking for, continuing to surprise them with the depth of our catalog.

Jeff Wilke (ex-CEO, World Wide Consumer) recently highlighted at re:Mars our team's pioneering use of neural networks for recommendations - our first success from 4 years ago! In order to meet our customers rising expectations and ever expanding catalog of content, we've pushed the cutting edge of using deep learning for recommendations ever since. However, we're still not satisfied with the experience, and we need your help to move even faster.

If you are ready to truly make an impact on a product that is used by millions of people around the world, including your own friends and family, then we would love to talk to you.

Key job responsibilities
  • Being the lead engineer on a team, mentoring junior engineers, ensuring the right development practices are followed.
  • Being very hands-on; working with an engineering team to manage the day-to-day development activities by leading architecture decisions, participating in design reviews, code reviews, and implementation.
  • Maintaining current technical knowledge to support a rapidly changing technology stack, always being on the look out for new technologies and working with management and development teams in exploring new technologies.
  • Communicating with users, other technical teams, and senior management to collect requirements, describe software product features, technical designs, and product strategy.

A day in the life
Few examples of the things you will work on in routine:
  • Using Neural Networks and Deep Learning techniques to find titles that customers will enjoy
  • Build and operate services that deliver millions of recommendations per second
  • Extend models and algorithms to support our ever growing ways of consuming content (subscriptions, live, rentals etc), dealing with unique challenges such as observational bias and rapidly scaling dimensions
  • Constantly experimenting with changes to the underlying algorithms and models to deliver relevant content to a wide variety of customer experiences.

About the team
Our team helps customers discover enjoyable videos they are most likely to watch. We achieve this through personalization services powered by machine learning algorithms/models. We are either exploring or leveraging: residual networks for surfacing more of our catalog, auto encoders and clustering to identify niche content carousels, attention networks to better understand what customers are currently into, reinforcement learning to optimize for the long term, graph convolution networks to understand the complex interaction of our customers with the videos they enjoy (or don't), and transfer learning to optimize to different customer objectives. On joining our team, you will not only be exposed to the cutting edge of machine learning research, but you'll collaborate with a talented team of engineers and scientists to create services to run these predictions on distributed systems at incredible scale and speed. As a member of the Prime Video recommendation team, you will spend your time as a hands-on engineer and a technical leader. You will play a key role in building and guiding software products and features from the ground up. You will use a wide range of technologies, programming languages and systems. Your responsibilities will include all aspects of software development. At the end of the day, you will have the reward of seeing your contributions delight Prime Video customers worldwide.


  • 1+ years of experience contributing to the system design or architecture (architecture, design patterns, reliability and scaling) of new and current systems.
  • 2+ years of non-internship professional software development experience
  • Programming experience with at least one software programming language.


  • Master's degree or PhD in Computer Science or equivalent
  • Experience with critical, 24x7 systems
  • Experience building complex software systems that have been successfully delivered to customers
  • Experience building large scale distributed services
  • Experience building and deploying machine learning models
  • Knowledge of professional software engineering practices & best practices for the full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations
  • Experience designing and deploying Big Data pipelines with tools such as Hadoop, Spark or MapReduce.
  • Strong system design and architecture experience.


Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit

Company Information

Amazon is guided by four principles: customer obsession rather than competitor focus, passion for invention, commitment to operational excellence, and long-term thinking. We are driven by the excitement of building technologies, inventing products, and providing services that change lives. We embrace new ways of doing things, make decisions quickly, and are not afraid to fail. We have the scope and capabilities of a large company, and the spirit and heart of a small one. Together, Amazonians research and develop new technologies from Amazon Web Services to Alexa on behalf of our customers: shoppers, sellers, content creators, and developers around the world. Our mission is to be Earth's most customer-centric company. Our actions, goals, projects, programs, and inventions begin and end with the customer top of mind. You'll also hear us say that at Amazon, it's always "Day 1." What do we mean? That our approach remains the same as it was on Amazon's very first day - to make smart, fast decisions, stay nimble, invent, and focus on delighting our customers.

Dice Id : amazon15
Position Id : 1941622
Originally Posted : 4 months ago

Similar Positions at Amazon