Data Scientist II, Fraud & Risk

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

Hands-on data science work on fraud and risk models for an identity verification company. The role sits on the Fraud & Risk Data Science team and builds deep learning models for fraud detection, risk management, and identity verification.

• Fraud and scams

What you'd do

• Design, develop, and implement deep learning models such as transformers, CNNs, and LSTMs for fraud and risk problems.
• Build and tune models that work across tabular records, text, point clouds, and images.
• Take part in the full ML lifecycle, from data exploration and feature engineering through training, evaluation, and deployment.
• Make routine technical decisions and work with colleagues across teams to deliver project goals.
• Track advances in AI and machine learning and apply them to real-world problems.
• Explain results and insights to both technical and non-technical audiences.

What it asks for

• Bachelor's degree with substantial related experience, or a Master's with relevant experience, in computer science, statistics, math, engineering, or a related field.
• 2-4 years developing and deploying deep learning models such as transformers, CNNs, and LSTMs.
• Experience with diverse data types including tabular data, text, point clouds, and images.
• Proficiency in Python and major ML frameworks such as PyTorch, TensorFlow, or scikit-learn.
• Foundational knowledge of ML algorithms, model evaluation, and data pipeline development.
• Experience deploying and monitoring models in production (real-time inferencing preferred).
• Experience with LLMs and agentic AI frameworks such as LangChain, LangGraph, or Ray (preferred).

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.