Applied Scientist, Seller Partner Trust and Store Integrity Science - Global Risk Intelligence and Prevention

Written by the T&S Network from Amazon's posting.

Builds ML risk detection models that find bad sellers and marketplace abuse across the full seller lifecycle, from registration through ongoing account management, on Amazon's global stores. Sits within GRIP Science, the detection engine of TSI Science, which blocks bad sellers across 24 marketplaces.

• Fraud and scams

What you'd do

• Design and build predictive risk models using graph-based and network analysis to spot bad actors
• Build interpretability pipelines that explain model decisions to enforcement and seller experience teams
• Turn investigation patterns from risk programs into automated detection systems and set priorities
• Work with engineering to deploy models and with operations and verification teams to measure detection effectiveness

What it asks for

• PhD, or Master's plus 4+ years in CS, CE, ML or a related field
• Programming experience in Java, C++, Python or a related language
• Experience in algorithms, data mining, distributed computing, or similar areas
• Hands-on grounding in machine learning and large language models, from architecture through training and inference
• Working command of deep learning, classical machine learning and statistics
• Track record turning ambiguous business problems into ML solutions
• Professional software development experience (preferred)

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Amazonnorth_east before you apply. If we got something wrong, report this listing.