Staff Data Scientist - Digital Intelligence

Job Summary

Socure is the leading provider of digital identity verification and fraud prevention solutions, using AI and machine learning to power accurate identity trust decisions. Our mission is to eliminate identity fraud and ensure online trust across industries. We are seeking a Staff Data Scientist to join our Digital Intelligence team.

Job Responsibilities

• Lead high-impact machine learning and feature-development initiatives across device, network, browser, mobile, session, and behavioral intelligence.
• Own ambiguous fraud and identity risk problems where data quality, label reliability, adversarial behavior, customer impact, and product tradeoffs must be evaluated together.
• Develop production risk signals and models that balance fraud detection, false-positive risk, coverage, latency, explainability, robustness, and operational maintainability.
• Build and guide scalable feature-engineering approaches for high-cardinality, sparse, noisy, and platform-dependent telemetry.
• Investigate complex signal patterns such as spoofing, emulator behavior, automation, proxy/VPN usage, low-entropy fingerprints, telemetry gaps, device fragmentation, and over-linkage risk.
• Define evaluation methods for Digital Intelligence signals, including holdout design, leakage checks, drift monitoring, adversarial robustness, customer impact analysis, and long-term signal stability.
• Influence telemetry collection, data contracts, feature logging, model monitoring, and production readiness in partnership with engineering, product, risk, and platform teams.
• Translate open-ended product, customer, and fraud-risk questions into clear data science approaches, measurable hypotheses, and production-ready signal roadmaps.
• Raise team standards for feature quality, model validation, explainability, documentation, and risk-signal governance.
• Communicate technical recommendations, tradeoffs, limitations, and results clearly to data science peers, engineering partners, product stakeholders, risk teams, and senior leadership.
• Mentor data scientists by improving problem framing, modeling judgment, validation rigor, code quality, and ability to operate independently in ambiguous domains.

Job Requirements

• Master’s or Ph.D. in Computer Science, Machine Learning, Statistics, Mathematics, Data Science, or a related quantitative field.
• 12+ years of experience in data science, applied machine learning, statistical modeling, or related technical roles.
• Significant experience building, deploying, validating, and improving production machine learning models, risk signals, or decisioning systems.
• Strong background in fraud detection, identity verification, trust and safety, anomaly detection, cybersecurity, risk modeling, or another adversarial data domain.
• Expert-level SQL skills and extensive experience working with large-scale, complex, noisy datasets.
• Strong proficiency in Python and distributed data processing frameworks such as Spark, PySpark, or equivalent tools.
• Deep understanding of supervised learning, unsupervised learning, anomaly detection, feature engineering, model evaluation, production monitoring, and statistical validation.
• Demonstrated ability to work with imperfect labels, delayed outcomes, telemetry artifacts, instrumentation gaps, and changing fraud patterns.
• Strong judgment across data quality, modeling approach, feature design, explainability, operational complexity, and business impact.
• Experience influencing data architecture, instrumentation, feature logging, and product direction through technical credibility rather than direct authority.
• Excellent communication skills, including the ability to explain complex data science decisions and risk tradeoffs to technical and non-technical audiences.
• Strong mentorship skills and a track record of improving the technical quality and judgment of other data scientists.

Preferred Qualifications

• Experience with device intelligence, browser/mobile fingerprinting, behavioral biometrics, network intelligence, VPN/proxy detection, entity resolution, or graph-based risk signals.
• Experience designing features from high-cardinality categorical data using techniques such as aggregation, frequency encoding, target encoding, embeddings, graph features, or representation learning.
• Experience with streaming, near-real-time, or low-latency decisioning systems.
• Familiarity with adversarial modeling, robust ML, privacy-preserving ML, interpretable ML, or responsible AI practices.
• Hands-on experience with ML frameworks such as scikit-learn, XGBoost, TensorFlow, PyTorch, or similar.
• Experience setting standards for model explainability, feature governance, validation methodology, or production ML observability.