Staff Data Scientist - Fraud & Risk

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

Builds and runs the deep learning and ML models behind fraud detection, risk management and identity verification for Socure's core products. Sits in the Fraud & Risk Data Science team, covering the models that decide whether identities and transactions are trusted.

• Fraud and scams
• AI misuse and jailbreaks

What you'd do

• Design and build deep learning models such as transformers, CNNs/RNNs and graph learning for fraud and risk problems.
• Build models on tabular data, text, point clouds and images.
• Own the full ML lifecycle from data exploration and feature engineering through deployment and production monitoring.
• Take ownership of project outcomes, data quality and delivery timelines, and escalate blockers early.
• Mentor peers and junior data scientists on experimentation and iteration.
• Work with Product, Engineering and Risk teams to define data requirements and turn findings into decisions.
• Research new data sources and novel algorithms for fraud detection.

What it asks for

• Graduate degree (Master's or PhD) in computer science, statistics, applied math, data science or a related field, or equivalent work experience.
• 8+ years in data science or machine learning, ideally in a high-growth tech or fintech setting.
• Experience in fraud prevention, risk modeling or identity verification.
• Years of building and shipping deep learning models such as transformers, CNNs/RNNs and graph learning.
• Experience with tabular, text, point cloud and image data.
• Strong Python and SQL, plus major ML frameworks such as PyTorch, TensorFlow or scikit-learn.
• Experience deploying and monitoring models in production.

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