RBS Tech is committed to support business growth across WW Retail through standardization, simplification and automation.
We are developing an automated solution Sherlock to Walk the Store’ (WTS) in a scalable fashion. Sherlock uses Machine Learning / Deep Learning to search across Amazon’s selection, looking for products that might have errors and that may disrupt customers’ shopping experiences.
The suspect items are reviewed for validation and fixed, in the process helping the machine to learn.
Last year the team worked on identifying Text attribute mismatch issues, by applying various deep learning techniques and an ensemble of classifiers.
The errors identified by Sherlock are consumed and fixed by multiple business teams in Amazon Retail Organization. This year, we are have three very interesting and highly ambiguous use case like image issues, variations problems, expanding the scope of Text attribute mismatches.
All these use cases are ideal candidates to apply various Deep learning techniques.
We are hiring applied scientists who can creatively solve these use cases.
As an Applied Scientist in RBS Sherlock team, you will work with talented peers to develop novel algorithms and modeling techniques to solve these high impact issues.
You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in artificial intelligence.
You will collaborate with other scientists and work in a fast paced team environment. Your work will directly impact our customer experience, save millions in concessions.
You will constantly stretch the boundaries of Machine Learning to tackle business challenges.
If you are customer obsessed, self-driven, tenacious and analytical, you will have fun solving our business problems of unprecedented scale.
As an experienced machine learning scientist, you will help research and develop new computer algorithms leveraging both classical and deep learning techniques.