SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Socure is building identity trust infrastructure for the digital economy, verifying identities in real time and stopping fraud at scale. The Watchlist platform screens hundreds of millions of entities across sanctions lists, PEP databases, and adverse media sources for banks, fintechs, and payment companies globally.
As a Staff Data Scientist on the Watchlist Data Science team, you will own the hardest technical problems in entity matching and classification. This is a senior individual contributor role with broad technical ownership and direct impact on a product that helps financial institutions manage sanctions and AML risk.
Key responsibilities include:
**Data Quality & Enrichment:** Improve quality, coverage, and freshness of underlying data through next-generation ingestion pipelines. Design rigorous data quality analysis to identify anomalies and ensure high-fidelity inputs for model training. Apply NLP and AI to classify and enrich raw source data into normalized schemas, extracting structured entity attributes from unstructured sanctions, PEP, adverse media, and enforcement sources. Expand multilingual capabilities across Latin and non-Latin scripts.
**Entity Resolution:** Build and improve NLP systems that consolidate watchlist identity representation. Develop Information Extraction and Named Entity Recognition (NER) pipelines to deduplicate entities across lists and resolve aliases into canonical profiles. Develop approaches to handle entity profile evolution as names, aliases, and sanctions status change. Measure and benchmark entity resolution quality.
**Match Engine & Risk Scoring:** Design and scale advanced NLP models and algorithms for real-time name matching and identity classification across diverse, multilingual unstructured data sources. Build multi-signal risk scoring combining name similarity, entity type, geography, list type, and other attributes into unified, calibrated risk scores. Maintain benchmarking frameworks, golden datasets, and regression tests.
**Analytics, Tuning & Evaluation:** Build models and analytics helping customers tune screening thresholds to their risk appetite. Develop backtesting and counterfactual analysis capabilities. Design evaluation frameworks for AI-powered autonomous decision systems, defining correct behavior and monitoring for drift in production.
**AML Risk Detection:** Build mathematical analysis and feature engineering to detect AML risk patterns across transaction data and payment message fields. Develop and maintain AML taxonomy and risk signal library. Apply graph-based methods to surface indirect risk exposure.
**Research & Technical Leadership:** Lead technical initiatives across Watchlist Data Science and shape the team's long-term approach to entity matching, enrichment, and AI. Collaborate with Product and Engineering to translate research into production-grade systems. Stay current with advances in NLP, large language models, and entity resolution. Mentor peers and contribute to technical rigor.
**Requirements:**
- Master's or PhD in Computer Science, Computational Linguistics, Statistics, Applied Mathematics, or related field; or equivalent professional experience
- 7+ years of experience in data science or machine learning, with meaningful work in NLP, entity resolution, or information extraction
- Experience in AML, sanctions screening, adverse media, or financial crime detection strongly preferred
- Hands-on experience building and deploying NLP pipelines for entity extraction, NER, and record linkage at production scale
- Familiarity with multilingual NLP and non-Latin script processing is a strong plus
- Experience with LLMs and agentic AI frameworks (e.g., LangChain/LangGraph) is a plus
- Strong proficiency in Python and major ML libraries (PyTorch, spaCy, HuggingFace Transformers)
- Strong SQL proficiency and experience with large-scale data pipelines and production ML systems
- Excellent communication skills to translate model performance tradeoffs into compliance and business language for non-technical audiences
- Must be located in one of Socure's talent hubs: New York, San Francisco, Seattle, or Miami
- No sponsorship available
