Socure
Senior Data Scientist - Digital Intelligence, Device Signals
$150K–$185K
Hybrid - San Francisco, CA +2 · Senior · Full-time · Posted Apr 1, 2026
- Location
- Hybrid - San Francisco, CA
Hub - San Francisco
Hub - Miami - Experience
- 6+ years in data science or applied machine learning, including experience working in production environments.
- Education
- Master’s degree (or equivalent practical experience) in Computer Science, Machine Learning, Statistics, or a related quantitative field.
About the job
Develops machine learning features and models using device, network, and behavioral data to support fraud prevention and identity verification.
What you'll do
- Design and deploy ML systems for device identification, anomaly detection, and fraud prevention; develop scalable data pipelines and production ML workflows.
- Investigate complex fraud signals, translate business problems into modeling approaches, and validate models through experiments and testing.
- Collaborate with engineering, product, and risk teams; communicate findings and mentor junior data scientists.
What they ask for
- Master’s degree or equivalent practical experience in Computer Science, Machine Learning, Statistics, or a related quantitative field.
- 6+ years in data science or applied machine learning, including production experience.
- Excellent SQL skills; proficiency in Python and distributed computing tools such as Spark or PySpark.
- Experience deploying and maintaining production ML models, using ML frameworks, and designing and interpreting experiments.
Nice to have
- Background in fraud detection, behavioral biometrics, anomaly detection, or adversarial modeling.
- Knowledge of browser/mobile fingerprinting, VPN/proxy detection, or telemetry signal processing.
Pay
$150K – $185K USD base salary
Tools
SQL, Python, Spark, PySpark, scikit-learn, XGBoost, TensorFlow
AI focus
Applied machine learning for device identification, fraud prevention, anomaly detection, and identity verification using device, network, and behavioral data.
Model-written summary · the original posting is authoritative