Fraud & Risk Data Scientist II — Deep Learning for Identity

Socure; Miami (FL); On-site; USD 140,000 - 170,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Professional growth

Collaborative culture

Job summary

Socure is seeking a Data Scientist II to join our Fraud & Risk Data Science team. You will work hands-on with deep learning models, collaborating to deliver scalable fraud detection and identity verification solutions.

This role emphasizes autonomy and cross-functional collaboration to drive impactful results. The position focuses on end-to-end ML lifecycle, from data exploration and feature engineering to model training, evaluation, deployment, and monitoring, with ongoing learning and

Qualifications

• Bachelor’s degree in Computer Science, Statistics, Mathematics, Engineering, or related field.
• 2–4 years hands-on experience developing and deploying deep learning models (transformers, CNNs, LSTMs).
• Experience with diverse data modalities: tabular, text, images, point clouds.

Responsibilities

• Design, develop, and implement advanced deep learning models to address fraud and risk challenges.
• Build and optimize models using tabular data, text, images, and other modalities.
• Own assigned tasks and drive project goals with minimal supervision.
• Participate in data exploration, feature engineering, training, evaluation, and deployment.

Skills

Python

Deep learning

ML libraries

Model deployment

Communication

Education

Bachelor’s degree in CS/Stats/Math

Master’s degree

Tools

PyTorch

TensorFlow

scikit-learn

LangChain

Ray

Job description

Socure is seeking a Data Scientist II to join our Fraud & Risk Data Science team. You will work hands-on with deep learning models, collaborating to deliver scalable fraud detection and identity verification solutions.

This role emphasizes autonomy and cross-functional collaboration to drive impactful results. The position focuses on end-to-end ML lifecycle, from data exploration and feature engineering to model training, evaluation, deployment, and monitoring, with ongoing learning and