Location
London

Hours
Full Time

Salary
Competitive, commensurate with experience

About the Role
Orchestrating the selection of one out of tens of millions of ads, honoring advertiser targeting intent for hundreds of thousands of advertisers while ensuring a great shopper experience for billions of shoppers millions of times per second on a latency of tens of milliseconds is a complex challenge. The Demand Retrieval team within the Amazon DSP organisation tackles this by developing and operating machine learning models that match ad opportunities with the most relevant ads to deliver the right messages to the right customers at the right time.

As an Applied Scientist, you will optimize ad matching for Amazon's programmatic advertisement products. You will lead the design and implementation of solutions for performance sourcing, leveraging behavioural information on customers' interactions with Amazon and other owned businesses, as well as contextual bid request data, to predict conversion propensity and drive better advertising campaign outcomes.

Your work will impact multi-billion dollar businesses, and you will be responsible for designing, testing, and delivering significant breakthroughs for Amazon's advertising business. You will collaborate closely with product and engineering teams, bringing your ideas to the table and iterating rapidly in a fast-paced environment.

Key responsibilities include designing and implementing deep learning models across verticals, geographies, and ad formats; investigating new ML techniques such as multi-task learning; improving model performance, generalization, and scalability; working with large datasets and high-throughput production systems; prototyping and testing hypotheses; and staying current with the latest research in machine learning for recommender and advertising systems.

You will be immersed in Amazon’s advertisers and their objectives, thinking long-term about how to translate those objectives into products and technical capabilities.

Experience
- PhD or Master's degree with experience in Computer Science, Computer Engineering, Machine Learning, or related research fields
- Programming experience in Java, C++, Python, or related languages
- Proven experience building machine learning models for business applications
- Expertise in state-of-the-art deep learning model architecture design, training, optimization, and model pruning

About you
- Strong technical ability with excellent teamwork and communication skills
- Motivated to achieve business results in a fast-paced environment
- Ability to rapidly prototype and test multiple hypotheses in ambiguous settings
- Passionate about delivering impactful solutions that drive business outcomes

Qualifications
- Preferred experience in retrieval and ranking systems applied to advertising or recommender systems
- Deep understanding of modern ML techniques and methodologies
- Software engineering and data processing skills to deploy models at scale