Orchestrating the selection of one out of tens of millions of ads, honoring advertiser targeting intent for hundreds of thousands of advertisers while ensuring great shopper experience for billions of shoppers millions of times per second on a latency of tens of milliseconds is not a trivial task. The demand retrieval team within the Amazon DSP organisation deals with this challenge, developing and operating machine learning models that match ads opportunities with the most relevant ads to deliver the right messages to the right customers at the right time.

We are looking for a Software Engineer to optimize ad matching for Amazon’s programmatic advertisement products. In this role you will work at the forefront of high scale low latency customer-facing advertising systems. You will bring best practices in MLOps and Software Engineering to process large datasets and enable the development foundation ML models in advertising. Your work will affect multi-billion dollar businesses, and you will be responsible for designing, testing and delivering significant breakthrough's for Amazon's business.

You will embody engineering rigor, designing and executing proofs of concept that validate the technical efficacy and business value of our product hypotheses. Then bringing them into production, balancing speed of execution with operational excellence.

Successful candidates will have strong technical ability, self driven, excellent teamwork, and communication skills, and a motivation to achieve business results in a fast-paced environment.

Key job responsibilities
* Work side by side with our scientists to deliver code changes impacting our ads stack
* Rapidly prototype and test many possible hypotheses/implementation alternatives in a high-ambiguity environment, making use of both quantitative analysis and business judgement
* Work with very large datasets.
* Integrate successful experimental results into large-scale, highly complex Amazon production systems capable of handling 100,000s of transactions per second at low latency.
* Automate, monitor and self heal our systems

A day in the life
You will partner with our product teams, bringing your own ideas to the conversation and aligning on work, adjusting priorities based on business requirements and fast iteration on experiments. You will work with scientists on rapid data gathering prototypes and analyses and represent the rigor of engineering in the conversation; you will engage with scientists, product and finance to align on the benefits of the proposed approach. You will help harmonise our product stack, enabling simple monitoring and self healing that allow us to do more with less through automation and rapid diagnostic tools.

About the team
The Demand Retrieval team is responsible for designing, implementing, deploying and operating machine learning models that match bid opportunities to ads demand based on performance, campaign delivery, and targeting objectives specified by advertisers. We measure the success of our approaches based on offline experimentation and and online metrics that measure the impact of our matching models on campaign KPIs (e.g.: cost per action, return on ads investment, budgets delivered, and targeting precision).