No applications. Teams find and message you directly.
Join Socure as a Staff Data Scientist to develop NLP pipelines and enhance identity resolution for real-time client verification.
Socure is a digital identity verification platform focused on risk assessment and fraud prevention, serving over 3,000 clients including 19 of the 20 largest banks in the USA.
- Develop NLP pipelines for entity extraction from sanctions lists and other sources.
- Improve name matching and identity resolution considering aliases and multilingual data.
- Scale matching engine and risk assessment models for real-time client verification.
- Create test sets and quality metrics for AML screening.
- 7+ years in Data Science or ML with experience in NLP, entity resolution, or information extraction.
- Practical experience in deploying NER and NLP pipelines for record matching.
- Proficient in Python and ML libraries such as PyTorch, spaCy, or HuggingFace Transformers.
- Strong SQL skills and experience with large data pipelines and production ML.