Applied Scientist II, Ads Moderation Automation and Relevance System (MARS)

Job summary
Advertisements Moderation Automation and Relevance System (MARS) team is responsible for ensuring that ads are policy compliant, relevant and of good quality, leading to higher conversion for the sellers and providing a great experience for the customers. We deal with one of the world’s largest ads catalog, handle billions of requests a day with plans to grow it by order of magnitude and use automated systems to validate tens of millions of ads submitted by thousands of merchants in multiple countries and languages. With a broad mandate to experiment and innovate, we are growing at an unprecedented rate with a seemingly endless range of new opportunities.

In this role, you will build advanced algorithms for creative performance insights generation requiring expertise in Machine Learning and Deep Learning. These models need to scale to hundreds of requests per second. You will collaborate with engineers and other scientists to build, train and deploy these models to recommend insights to Advertisers. You will propose models, validate these offline and run A/B tests to validate them online. As part of these activities, you will develop production level code that enables our business goals.

Key job responsibilities
1. Identify opportunities to improve existing ML solutions and constantly look out for new opportunities to apply ML with leadership 2. Execute on the opportunities identified and new initiatives to launch ML models 3. Monitor the models and iterate on 1 and 2 till we convert potential impact to reality

Basic Qualifications

Masters in Computer Science, Computer Engineering or related technical discipline
Expertise in Machine Learning and Deep Learning
3+ years of relevant applied sciences experience
A deep understanding of algorithms, ML, and some exposure to big data systems
Expertise in programming languages (python, java) typically used for deep neural network training and launch of models

Preferred Qualifications

PhD in Machine Learning or equivalent
Significant peer reviewed scientific contributions in relevant field
Expertise on a broad set of practical experience of applying techniques, including Deep Learning, Natural Language Processing, statistics, Recommendation systems and or information retrieval
Strong fundamentals in problem solving, algorithm design and complexity analysis
Expert in more than one more major programming languages (Java, C++ or similar) and at least one scripting language (Python, or similar)
Great verbal and written communication and presentation skills, ability to convey rigorous mathematical concepts and considerations to non-experts
A track record of shipping models to production on time
Prior experience with agile methodologies

Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation.