Senior Data Scientist – International eKYC, Identity Graph

This is a fully remote position, open to applicants in United States.

📋 Description

• Spearhead the design, development, and implementation of machine learning and graph-based algorithms for global entity resolution, identity trust scoring, and anomaly detection across diverse, country-specific datasets.

• Create reusable matching and linking frameworks that function across various ID schemes (such as national ID numbers, passports, voter IDs, mobile accounts, and bank accounts) and local naming/address conventions.

• Construct probabilistic and rule-augmented models that can handle noisy, sparse, or partially labeled international data while ensuring explainability and compliance with regulatory requirements.

• Define and enhance the global extension of Socure’s identity graph, including schema design, linkage strategies, quality tiers, and confidence scoring that can be utilized by multiple products (Verify, KYC, watchlists, fraud detection).

• Design and execute robust data quality and monitoring frameworks for international identity data (covering aspects like stability, drift, regional bias, and label quality) and seamlessly integrate them into modeling and production monitoring workflows.

• Oversee the experimentation strategy for key international eKYC projects: create offline evaluations and online A/B tests that consider local ground truth constraints and data sparsity.

• Establish success metrics that balance approval rates, fraud detection, and regulatory/operational constraints for each market.

• Assess lift, stability, and fairness trade-offs and guide go/no-go decisions in collaboration with Product and Engineering teams.

• Contribute to model governance documentation and assist in responding to regulators and large enterprise clients concerning model logic, data provenance, fairness, and monitoring for international markets.

⛳️ Requirements

• Master’s or Ph.D. in Computer Science, Data Science, Machine Learning, Statistics, Mathematics, or a related discipline, or equivalent practical experience.

• 6+ years of hands-on applied machine learning/data science experience (4+ years with a Ph.D.), including responsibility for production models and pipelines in high-stakes domains (fraud, risk, identity, payments, credit, or similar).

• Significant prior experience with international or multi-region products is highly desirable (for example, cross-country KYC, credit risk, payments, or compliance systems).

• Expert-level proficiency in Python and SQL, with substantial experience in distributed data processing (such as Spark/PySpark, Databricks, or similar) on very large datasets.

• Extensive experience in designing, training, and deploying models for classification, ranking, anomaly detection, and/or graph learning, including:

• Feature engineering for noisy/heterogeneous identity data.

• Robust evaluation under label sparsity and feedback delays.

• Calibration and thresholding tailored to regional risk and regulatory constraints.

• Demonstrated expertise with graph technologies (e.g., Neo4j, AWS Neptune, GraphFrames, DGL, PyTorch Geometric) and graph algorithms (entity resolution, link prediction, community detection, label propagation) at scale.

🏝️ Benefits

• Offers Equity

• Offers Bonus