Compliance Tech Team supports Amazon’s mission of offering the widest selection of products available, while protecting customers from recalled or unsafe products.
We develop a suite of systems (manual, supervised, and fully automated) that enable product classification according to various taxonomies.
These include systems that :
1) orchestrate and automate operational workflows,
2) perform data extraction from documents (such as technical specifications) and images (such as product labels) associated with the products, making use of the latest NLP advances,
3) perform standard symbol identification in documents and natural scenes,
4) make classification recommendations and surface potential risks
In building these systems we leverage a mix of in-house and public AWS technologies such as Lambda, Fargate, Step Functions, SageMaker, Textract, Comprehend, Translate, Rekognition and DeepLens.
This is an exciting opportunity to gain valuable experience in regulatory compliance with a vibrant and fast-growing company!
We are looking for Software Development Engineers / Applied Scientists with strong analytical and problem solving skills, who will participate in the full development cycle from design and implementation to documentation and maintenance.
The successful candidate will have an entrepreneurial spirit and be passionate about developing reliable, efficient, and maintainable data analysis solutions that provide users with robust information solutions.
Key Responsibilities :
Participate in the design, development, implementation, testing and documentation of large-scale distributed software applications, tools, systems and services;
Translate functional requirements into robust, scalable, supportable solutions that work well within the overall system architecture;
Participate in the full development cycle, end-to-end, from design, implementation, and testing to documentation, delivery and maintenance;
Produce comprehensive, usable software documentation;
Evaluate and make decisions around the use of new or existing software products and tools.
MS. in Computer Science, Machine Learning, Operational Research, Statistics or a related quantitative field
2+ years of hands-on experience in predictive modeling and analysis
Strong algorithm development experience
Skills with Java, C++, or other programming language, as well as with R, MATLAB, Python or similar scripting language
Advanced level of written and spoken English.
The ideal candidate will have a PhD in Mathematics, Statistics, Machine Learning, Economics, or a related quantitative field, and 3+ years of relevant work experience, including :
Significant peer reviewed scientific contributions in relevant field.
Extensive experience applying theoretical models in an applied environment.
Expertize on a broad set of ML approaches and techniques, ranging from Artificial Neural Networks to Bayesian Non-Parametrics methods.
Strong Experience in Structured Prediction and Dimensionality Reduction.
Expert in more than one more major programming languages (C++, Java, or similar) and at least one scripting language (Perl, Python, or similar).
Proven track record of production achievements in language, search and personalization.
Strong fundamentals in problem solving, algorithm design and complexity analysis.
Strong personal interest in learning, researching, and creating new technologies with high commercial impact.
Experience with defining organizational research and development practices in an industry setting.
Proven track in leading, mentoring and growing teams of scientists (teams of five or more scientists).
Strong communication and data presentation skills