Senior Data Scientist, AML & NLP Systems

Apply; New York, Northern (NY, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Socure is hiring a Staff Data Scientist for the Watchlist Data Science team. You will tackle hardest problems in entity matching, NLP model development, and productionizing research for AML risk screening across global data sources.

You will scale real-time matching, build multilingual NLP pipelines, and lead technical initiatives with cross-functional partners to deliver robust, scalable solutions.

Qualifications

• 7+ years of data science or ML experience, with NLP, entity resolution, or information extraction.
• AML domain knowledge or sanctions screening experience preferred.
• Hands-on NLP pipelines for entity extraction and NER at production scale.
• Multilingual NLP and non-Latin script processing a strong plus.
• Experience with LLMs and agentic AI frameworks (LangChain/LangGraph) is a plus.
• Strong Python and ML libraries (PyTorch, spaCy, HF Transformers).
• Strong SQL and large-scale data pipelines and production ML systems.

Responsibilities

• Scale real-time name matching and classification across multilingual data.
• Develop NLP pipelines for NER and information extraction.
• Lead technical initiatives across Watchlist DS and mentor peers.
• Collaborate with Product and Engineering to production-grade systems.
• Benchmarking, testing, and drift monitoring in production.

Skills

NLP

Entity resolution

Information extraction

Python

PyTorch

spaCy

HuggingFace Transformers

SQL

LangChain

LangGraph

PostgreSQL

Education

Master's or PhD in CS

Equivalent professional experience

Tools

LangChain

LangGraph

PostgreSQL

Job description

Socure is hiring a Staff Data Scientist for the Watchlist Data Science team. You will tackle hardest problems in entity matching, NLP model development, and productionizing research for AML risk screening across global data sources.

You will scale real-time matching, build multilingual NLP pipelines, and lead technical initiatives with cross-functional partners to deliver robust, scalable solutions.