Senior Data Scientist (Fraud & AI)

TL;DR

Senior Data Scientist - Fraud Data Infrastructure & Automation (AI/ML): Transforming raw, complex datasets into actionable insights for fraud detection and identity verification with an accent on scalable data pipelines, agentic AI, and LLM-powered automation. Focus on building and optimizing models with diverse data types, owning data quality and integrity, and evaluating third-party vendors to improve products and decisioning systems.

Location: Remote in US; must be located within ~45 miles of New York, Miami, DC, Seattle, or San Francisco. No sponsorship available now or in the future.

Compensation: $170K - $200K

Company

hirify.global builds identity trust infrastructure for the digital economy, verifying good identities in real time and stopping fraud.

What you will do

• Design, build, and maintain scalable data pipelines and workflows using Spark, Airflow, or similar for analytics, fraud detection, and model development.
• Leverage agentic AI and LLMs to automate data exploration, anomaly detection, vendor evaluation, and investigative workflows.
• Build and optimize models using tabular data, text, point clouds, and images for fraud and identity use cases.
• Own data quality with monitoring, validation, and anomaly detection for critical datasets.
• Evaluate third-party data vendors through experiments assessing quality, coverage, and value.
• Collaborate with Product, Engineering, and Risk teams to define requirements and deliver insights shaping fraud and identity products.
• Lead end-to-end ML/analytics lifecycle and present findings to stakeholders.

Requirements

• Must be located within ~45 miles of New York, Miami, DC, Seattle, or San Francisco
• No sponsorship available
• Master’s or PhD in CS, Stats, Applied Math, Data Science, or equivalent.
• 5+ years in data science/ML, ideally in high-growth tech/fintech; experience in fraud, risk, or identity with noisy data.
• Proficiency in Python, SQL, ML libraries (PyTorch, TensorFlow, scikit-learn).
• Experience with data pipelines in distributed environments (Spark, Airflow, Databricks).
• Strong ML knowledge, model evaluation, and working with diverse data modalities.

Nice to have

• Experience with LLMs and agentic AI (LangChain, LangGraph, Ray).
• Ability to design agentic workflows for analytics and data quality.

Culture & Benefits

• High bar for responsibility, fast pace, critical thinking, ownership, and customer focus.
• Emphasis on continuous learning, effective communication, accountability, team development, decision making, and managing change.
• Mentorship and knowledge sharing in a culture of experimentation and rapid iteration.