Job Description

DESCRIPTION

Job summary
Advertising at Amazon is a fast-growing, multi-billion dollar business. It spans desktop, mobile and connected devices; encompasses ads on Amazon and a vast network of hundreds of thousands of third-party publishers; and extends across the US, EU, APAC, and an increasing number of international geographies.

The Supply Quality (SQ) group operates across all Amazon Advertising products to provide invalid traffic (IVT) filtration, viewability prediction and measurement, and content adjacency policy enforcement capabilities.

Within Supply Quality, the Traffic Quality (TQ) program leverages proprietary and third-party technology to provide invalid traffic (IVT) detection and filtration capabilities to Amazon DSP customers.

The TQ-3PS team is looking for Applied Scientists who enjoy working on creative machine learning algorithms and thrive in a fast-paced, fun environment. An Applied Scientist is responsible for solving inherently hard problems in advertising IVT detection using deep learning, self-supervised techniques, representation learning and advanced clustering. An ideal candidate should have strong depth and breadth of knowledge in machine learning, data mining and statistics. Traffic quality systems process billions of bid requests and ad-impressions per day, by leveraging cutting-edge open source technologies like Hadoop, Spark, Redis and Amazon's cloud services like EC2, S3, EMR, DynamoDB and RedShift. The candidate should have excellent programming and design skills to manipulate unstructured and big data and build prototypes that work on massive datasets. The candidate should be able to apply business knowledge to perform broad data analysis as a precursor to modeling and to provide valuable business intelligence. Above all, the candidate should be an innovator at heart and have a track record of resolving ambiguity to deliver results.

Key job responsibilities

• Define a long-term science vision for TQ-3PS, driven fundamentally from the needs of our advertisers and publishers, translating that direction into specific plans for the science team. Interpret complex and interrelated data points and anecdotes to build and communicate this vision.
• Identify and implement elegant statistical, deep learning and representation learning solutions to detect robotic and human traffic.
• Oversee the design, development, and implementation of production level code that handles billions of ad requests and impressions. Own the full development cycle: idea, design, prototype, impact assessment, A/B testing (including interpretation of results) and production deployment.
• Collaborate with engineers, product managers and related teams in Amazon Advertising to find technical solutions to complex IVT detection problems.
• Influence and continuously improve a sustainable team culture that exemplifies Amazon's leadership principles.

• PhD or equivalent Master's Degree plus 4+ years of experience in CS, CE, ML or related field
• A strong ability in statistical modeling and analysis to provide rigorous solutions that address business needs.
• Hands on development experience in Python, C++, Java, or other OOP language, and exposure to big data systems.
• Demonstrated evidence of building lasting relationships with the team and business stakeholders.
• Excellent verbal and written communication skills with the ability to effectively advocate technical solutions to research scientists, engineering teams and business audiences

• PhD in Computer Science, Statistics, Mathematics or related field, or equivalent professional experience.
• Prior experience with cloud computing (EMR, S3, EC2, Redshift) and big data tools (Spark, Hadoop, HDFS).
• Experience working on advertising solutions
• Expertise on a broad set of practical experience of applying techniques, including Deep Learning, statistics, NLP, Recommendation systems and graph based networks
• Demonstrated track record of dealing well with ambiguity, prioritizing needs, and delivering results in a dynamic environment.
• Significant peer reviewed scientific contributions in relevant field